diff --git a/.env.example b/.env.example new file mode 100644 index 0000000..0174f3a --- /dev/null +++ b/.env.example @@ -0,0 +1,3 @@ +# Base URL for the clapping API (no trailing slash) +# Used by the ClapButton component to GET counts and POST claps via sendBeacon +PUBLIC_API_URL="http://localhost:3000" diff --git a/src/components/ClapButton.astro b/src/components/ClapButton.astro new file mode 100644 index 0000000..80b4d4f --- /dev/null +++ b/src/components/ClapButton.astro @@ -0,0 +1,255 @@ +--- +export interface Props { + slug: string; +} + +const { slug } = Astro.props; +--- + +
+
+ +
+ + … +
+ + + + diff --git a/src/content/docs/becoming-productive/closing-the-loop.mdx b/src/content/docs/becoming-productive/closing-the-loop.mdx index 25997ab..5f6fd5d 100644 --- a/src/content/docs/becoming-productive/closing-the-loop.mdx +++ b/src/content/docs/becoming-productive/closing-the-loop.mdx @@ -3,6 +3,8 @@ title: Closing the loop description: How to make agents self-correct faster with autonomous feedback loops across tests, logs, CLIs, and manual QA automation. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; Efficient agent workflows depend on a closed feedback loop. Agents should be able to gather signals from tests, logs, and runtime checks continuously, without waiting for manual input on every step. @@ -14,12 +16,16 @@ The tips below focus on building that loop so agents can diagnose and fix issues 1. Make sure your agent writes tests for any regression it finds before attempting to fix actual code. If it doesn’t do this by itself, consider telling it so in your AGENTS.md. 2. Pay attention to how models assert the expected state. Many models tend to write leaky assertions, which only catch the exact issue they just reasoned about. + + ## Backend logs and database access 1. Make your app tee logs to a `*.log` file. This will allow agents to observe runtime behavior. Models are also good at adding their own temporary logs while debugging. 2. Make it easy for an agent to connect to your database via `psql` or `sqlite3`. You can even use this interface in place of database GUIs. 3. . + + ## Leverage CLIs 1. Models are trained _a lot_ on Bash. They breathe it and are very productive when they can process data through shell one-liners or quick Python scripts. @@ -34,6 +40,8 @@ Also, take a look at these skills: if you make/use interactive CLIs. Agents are pretty good at using GDB/LLDB via tmux. + + ## Automating web frontend QA Current frontier models are surprisingly capable of browsing websites, clicking around, and observing what happens, provided they are given the right tools. @@ -50,6 +58,8 @@ Also, take a look at these skills: - + + ## Automating mobile app QA You can also tell the agent to play with a phone simulator. @@ -64,3 +74,5 @@ Also, have a look at these skills: - - + + diff --git a/src/content/docs/becoming-productive/going-10x.mdx b/src/content/docs/becoming-productive/going-10x.mdx index d5d6981..8153514 100644 --- a/src/content/docs/becoming-productive/going-10x.mdx +++ b/src/content/docs/becoming-productive/going-10x.mdx @@ -3,6 +3,8 @@ title: Going 10x description: Tactics for running multiple coding agents in parallel while managing conflicts, quality, and long-term maintainability. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; {/* NOTE: "sometimes they are, for sure" is a pun, keep it verbatim */} @@ -22,6 +24,8 @@ Agentic engineering is like multicore CPUs. Agents aren’t always faster than h You can put this as a rule in your `AGENTS.md` file. 2. Avoid invoking tasks that would write to the same parts of the repository. + + ## Help! My agents are writing spaghetti!!! This is where vibe coding starts to diverge from agentic engineering. You, as a human, do serious work, and you must be held responsible for it. Models can make a mess because they are rewarded for task completion during training, not long-term architecture. This is (still) a human’s job. @@ -42,6 +46,8 @@ Read more: - - + + ## Automated code reviews Automated review can run in parallel with implementation and catch obvious issues before a human reviewer spends time on them. @@ -72,3 +78,5 @@ PR review bots: Use these tools to reduce toil, not to skip ownership: don’t ask teammates to review code you haven’t reviewed yourself. - + + diff --git a/src/content/docs/becoming-productive/harness-engineering.mdx b/src/content/docs/becoming-productive/harness-engineering.mdx index ef884a6..bba1dfa 100644 --- a/src/content/docs/becoming-productive/harness-engineering.mdx +++ b/src/content/docs/becoming-productive/harness-engineering.mdx @@ -6,6 +6,8 @@ description: >- repeatable. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; Harness engineering is the practice of improving a coding agent's output @@ -88,6 +90,8 @@ It tends to produce documents that bring little meaningful value. Very often, this produces something akin to what you have just read. ::: + + ## Skills Agent Skills is an @@ -170,6 +174,8 @@ These writeups show how this can go wrong in practice: Hidden Unicode Tag characters were used to smuggle invisible instructions into a skill, which means visual source review alone may miss malicious behavior. + + ## MCP MCP is a protocol through which AI applications can connect to data sources @@ -236,6 +242,8 @@ points to well-known services. So... in such cases just make sure your agents will not perform destructive actions on your behalf 🙂. + + ## Subagents ![Subagents visualized](../../../assets/subagent.svg) @@ -257,6 +265,8 @@ Read more: - - + + ## Hooks Hooks are the part of the harness that runs deterministic logic around the @@ -287,6 +297,8 @@ Read more: - - + + ## When to use what If you are unsure which mechanism to reach for, use this rule of thumb: @@ -298,3 +310,5 @@ If you are unsure which mechanism to reach for, use this rule of thumb: | MCP | You need authenticated access to an external service that you use very frequently. | | Subagents | You can delegate a bounded or parallelizable task to keep the main thread smaller. | | Hooks | You have deterministic, mechanical logic meant to happen every time without depending on the model to remember it. | + + diff --git a/src/content/docs/becoming-productive/legal-compliance.mdx b/src/content/docs/becoming-productive/legal-compliance.mdx index 5ddf92f..74b0b20 100644 --- a/src/content/docs/becoming-productive/legal-compliance.mdx +++ b/src/content/docs/becoming-productive/legal-compliance.mdx @@ -5,6 +5,8 @@ description: >- including data handling, licensing, contracts, and accountability. --- +import ClapButton from "../../../components/ClapButton.astro"; + While technical sandboxes prevent agents from wiping databases, they do not prevent legal and compliance catastrophes. As a software engineer, you must be aware that using AI agents introduces @@ -38,6 +40,8 @@ Remember that a "do not collect my data" checkbox in settings is not the same level of legal security as an explicit zero data retention clause in terms of service. + + ## Copyleft contamination – IP infringement Another risk is introducing code with license obligations that conflict with the @@ -56,6 +60,8 @@ Ask the agent to explain the implementation in its own words and run a code search if a snippet looks distinctive enough that it may have been copied from a public project. + + ## Breach of contract and AI policies Many enterprises, especially in heavily regulated industries like fintech or @@ -65,6 +71,8 @@ Running an agent on a restricted project could be a direct breach of contract. Always ask your manager about your specific project’s AI policy before enabling an agent in that workspace. + + ## Accountability Agent-generated code does not shift legal or professional responsibility away @@ -78,3 +86,5 @@ it. That is why human review, provenance checks, and enterprise-specific compliance validation remain essential even when the implementation work is heavily automated. + + diff --git a/src/content/docs/becoming-productive/prompting-techniques.mdx b/src/content/docs/becoming-productive/prompting-techniques.mdx index 76d7412..53934c8 100644 --- a/src/content/docs/becoming-productive/prompting-techniques.mdx +++ b/src/content/docs/becoming-productive/prompting-techniques.mdx @@ -3,6 +3,8 @@ title: Prompting Techniques description: Practical prompting patterns for coding agents, from framing and execution guidance to multimodal input and walkthroughs. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; Once you have a sensible workflow, the next question is how to interact with the agent within it. @@ -79,6 +81,8 @@ Depending on the codebase, a useful pattern is to have several _golden_ files th - For example, if you have a component library, tell the agent to follow the implementation of the `ui/Button.tsx` component. - If you're doing repetitive module refactoring, make the changes in one golden module, then ask the agent to reproduce them in other modules. + + ## Steer the execution Once the task is clear, the next job is to keep execution on useful rails without micromanaging every action. @@ -131,6 +135,8 @@ The pattern is: Source: + + ## When text and code is not enough Sometimes the fastest way to explain a problem is not another painfully typed paragraph. @@ -169,6 +175,8 @@ Take a look at these utilities: - - + + ## Your exoskeleton Some prompting patterns are less about a single task and more about extending your reach as an engineer. @@ -209,3 +217,5 @@ Try pointing your agent at some website or Android APK where there’s something ### Issue pinpointer Got a huge log file, maybe a screenshot, and you need to identify the bug? Paste everything you have into your agent prompt and tell it to find the exact log lines itself. + + diff --git a/src/content/docs/becoming-productive/security.mdx b/src/content/docs/becoming-productive/security.mdx index 8580c3d..7beff9c 100644 --- a/src/content/docs/becoming-productive/security.mdx +++ b/src/content/docs/becoming-productive/security.mdx @@ -3,6 +3,8 @@ title: Security description: High-level security model for coding agents, from the Lethal Trifecta to harness defenses and real-world prompt injection failures. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; Security for coding agents is mostly about managing power, not eliminating it. @@ -55,6 +57,8 @@ The surprising answer is that it is not always some evil hacker. In this model, the attacker can also be you or your colleague. Sometimes it is just a human doing something careless and unattended. + + ## Cataclysms Many interesting attacks have already happened in the wild. @@ -68,6 +72,8 @@ The failure modes differ, but the outcomes are similar: one agent run gets too m - . A malicious issue in a public repository coerced an agent into pulling data from private repositories and leaking it through an automatically opened public pull request. + + ## Agent Security Toolbelt To reduce the chance of incidents like these, coding agent products usually adopt a permission-based security model. @@ -131,6 +137,8 @@ For example, you can write your own hook to block very specific Bash commands fr ![Using PreToolUse Hook for blocking Bash](../../../assets/bash-pre-tool-use-hook.svg) + + ## Do I need all of this? All the security mechanisms described in the previous section can usually be turned off. @@ -140,3 +148,5 @@ Think of it like living without antivirus software two decades ago. If you are unsure about the security of your setup, start with the default protections. Then gradually tune them or disable the parts that are too annoying for your workflow. + + diff --git a/src/content/docs/becoming-productive/the-workflow.mdx b/src/content/docs/becoming-productive/the-workflow.mdx index 1b14898..3814323 100644 --- a/src/content/docs/becoming-productive/the-workflow.mdx +++ b/src/content/docs/becoming-productive/the-workflow.mdx @@ -3,6 +3,8 @@ title: The Workflow description: "A baseline workflow for non-trivial agent tasks: brainstorm, plan, execute, review, and improve." --- +import ClapButton from "../../../components/ClapButton.astro"; + import { Steps } from "@astrojs/starlight/components"; import ExternalLink from "../../../components/ExternalLink.astro"; @@ -30,6 +32,8 @@ This knowledge splits into two parts: 2. The entire contents of the current thread, all past messages within it, and the space for future ones. We call this **context**. + + ## Obstacles Now that we know the tool we are working with, let's look at the biggest challenges we face when working with agents. @@ -70,6 +74,8 @@ As you load more code, rules, plans, and history, some of it must be dropped and For that reason, broad, complex prompts often underperform smaller, focused ones even when the nominal context window is huge. This is also why the phrase "use small threads" is repeated like a mantra. + + ## An ideal thread OK, so we know the tool, a **thread**, and we know the problems that come with it. @@ -115,6 +121,8 @@ Depending on your intent, some phases can be merged, shortened, or skipped. + + ## Threads are composable OK, so now we know how to structure work inside a single thread. @@ -131,3 +139,5 @@ Some tools allow you to refer to past threads directly (for example `@Past Chat` If your coding agent of choice does not provide such niceties, you can always fall back to sharing context through plain Markdown files. For example, you can run several brainstorming sessions, each on a different topic, and produce summary `*.md` files as outcomes. Then, in the execution thread, you _join_ all of that information when priming the context. + + diff --git a/src/content/docs/becoming-productive/what-not-to-do.mdx b/src/content/docs/becoming-productive/what-not-to-do.mdx index 30f398e..5e3becc 100644 --- a/src/content/docs/becoming-productive/what-not-to-do.mdx +++ b/src/content/docs/becoming-productive/what-not-to-do.mdx @@ -3,6 +3,8 @@ title: What Not to Do description: Common anti-patterns when working with coding agents and how to avoid them. --- +import ClapButton from "../../../components/ClapButton.astro"; + import { Steps } from "@astrojs/starlight/components"; import ExternalLink from "../../../components/ExternalLink.astro"; @@ -28,6 +30,8 @@ Specialisation matters: the same ground rules yield better results when an agent + + ## Taking recall for granted We often expect the model's recall not to be perfect when it comes to the data we provide, but we do not have the same concerns for recall on the model's training data, and you should. @@ -45,6 +49,8 @@ Instead, try to confront the agent with the data. + + ## Stacking assumptions Without validating each step, the agent may build on unstated assumptions, and when something goes wrong, the wrong turn is several layers deep. @@ -60,6 +66,8 @@ It is the same as a human writing long batches of code without running it. + + ## Accepting silent compliance The agents still have a problem with being too compliant. @@ -86,6 +94,8 @@ Put the push-back permission in `AGENTS.md` once and it applies to every thread, In Claude Code, you can use the brainstorm mode that automatically asks you clarifying questions, but at the expense of heightened token usage. ::: + + ## Running a thread until it rots Agents fare better with smaller context. @@ -110,6 +120,8 @@ The reset is not expensive—continuing the current thread is. Starting fresh is always cheaper than debugging a degraded thread. ::: + + ## Embedding your solution in the question Framing a prompt around your assumed solution narrows the search space before the agent has a chance to explore it. @@ -129,6 +141,8 @@ Maybe there is a better alternative. + + ## Treating the first attempt as final Remember that agents are not deterministic. Since the outputs on the same input differ, there is no guarantee that the first try yields an optimal answer. @@ -144,3 +158,5 @@ Remember that agents are not deterministic. Since the outputs on the same input The [parallel implementations](/becoming-productive/prompting-techniques/#parallel-implementations) pattern is built exactly for this. + + diff --git a/src/content/docs/expanding-horizons/model-pricing.mdx b/src/content/docs/expanding-horizons/model-pricing.mdx index 23ae3f6..7742d83 100644 --- a/src/content/docs/expanding-horizons/model-pricing.mdx +++ b/src/content/docs/expanding-horizons/model-pricing.mdx @@ -3,6 +3,8 @@ title: Model pricing description: "A concise guide to coding model pricing, including API costs, caching, and subscription tradeoffs." --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; There are two very different pricing worlds in AI tools: API pricing (pay per token) and app subscriptions (pay a flat monthly fee with usage limits). @@ -32,6 +34,8 @@ If you're integrating directly with an LLM API, lowering cost per request/sessio If you're using a coding agent, many of these optimizations are handled internally (prompt layout, caching, compaction). Your main cost levers are usually model choice and keeping tasks/threads scoped. + + ## Subscriptions Subscriptions are different from API billing. You pay a monthly fee for usage inside a product, usually with fair-use limits or soft/hard caps. These plans do not include raw API credits for your own apps. @@ -45,3 +49,5 @@ Common subscription options: - - - + + diff --git a/src/content/docs/expanding-horizons/threads-context-and-caching.mdx b/src/content/docs/expanding-horizons/threads-context-and-caching.mdx index 3b4c08e..bb7ab64 100644 --- a/src/content/docs/expanding-horizons/threads-context-and-caching.mdx +++ b/src/content/docs/expanding-horizons/threads-context-and-caching.mdx @@ -3,6 +3,8 @@ title: Threads, context, and caching description: Understand how thread length, context windows, prompt caching, and compaction shape agent reliability, speed, and cost. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; This page explains how agent threads are transformed into model input and why that directly affects reliability, latency, and cost. It covers context windows, prompt caching, and compaction so you can understand what changes as conversations get longer. @@ -24,6 +26,8 @@ Now (especially if you’re going to work with Anthropic models), go read this a - + + ## Prompt caching TL;DR: Prompt caching is an optimization for LLM APIs that lets the model _reuse previously computed internal context_ (especially the prefix of prompts like system instructions or examples), so repeated similar requests don’t have to be processed from scratch. @@ -31,6 +35,8 @@ TL;DR: Prompt caching is an optimization for LLM APIs that lets the model _reuse - - + + ## Compaction TL;DR: Compaction extends the effective context length for long-running conversations and tasks by automatically summarizing older context when approaching the context window limit. Compaction keeps the active context focused and performant by replacing stale content with concise summaries. @@ -38,3 +44,5 @@ TL;DR: Compaction extends the effective context length for long-running conversa - - - + + diff --git a/src/content/docs/expanding-horizons/what-to-read-next.mdx b/src/content/docs/expanding-horizons/what-to-read-next.mdx index 90abcbc..37c0613 100644 --- a/src/content/docs/expanding-horizons/what-to-read-next.mdx +++ b/src/content/docs/expanding-horizons/what-to-read-next.mdx @@ -3,6 +3,8 @@ title: What to read next description: Curated blogs and social feeds to follow for ongoing signal on agentic engineering, tooling, and model updates. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; If you want to stay sharp in agentic engineering, subscribe to these recommended feeds: @@ -19,6 +21,8 @@ Signal strength: 🟢 Low (~1 post/week), 🟡 Medium (~2-3 posts/week), 🔴 Hi - 🔴 - 🔴 + + ## Harness Developers - 🔴 @@ -29,6 +33,8 @@ Signal strength: 🟢 Low (~1 post/week), 🟡 Medium (~2-3 posts/week), 🔴 Hi - 🔴 - 🔴 + + ## Product and engineering blogs - 🟢 @@ -36,3 +42,5 @@ Signal strength: 🟢 Low (~1 post/week), 🟡 Medium (~2-3 posts/week), 🔴 Hi - 🟡 - 🟡 - 🟡 + + diff --git a/src/content/docs/getting-started/first-steps-in-mature-projects.mdx b/src/content/docs/getting-started/first-steps-in-mature-projects.mdx index 24071bf..7111557 100644 --- a/src/content/docs/getting-started/first-steps-in-mature-projects.mdx +++ b/src/content/docs/getting-started/first-steps-in-mature-projects.mdx @@ -3,6 +3,8 @@ title: First steps in mature projects description: A practical onboarding flow for using coding agents in mature codebases with predictable, low-risk, test-first delivery. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; import { Steps } from "@astrojs/starlight/components"; @@ -27,6 +29,8 @@ agent-friendly. Here are the high-level factors you should address when applying From a distance, these points are strongly correlated. You do not need to address each one separately. + + ## A first surgical feature delivery in 8 steps Let’s walk through a concrete case from a mature codebase using Cursor. @@ -118,6 +122,8 @@ For more examples, look out on the internet for shared agent threads, some quali - - + + ## Rules of thumb There are a few high-level rules you can follow when you jump into a new largeish project. @@ -173,6 +179,8 @@ Agents also like running `ls` in directories and calling `--help`; you can use t close to the code. A skill may just tell the agent about a utility and ask it to call for help. ::: + + ## Agent use must be negotiated In mature teams, maintainers may not accept higher agent autonomy, and that’s reasonable. @@ -194,3 +202,5 @@ In the end, you are the one who takes ownership of shipped code. ::: [^1]: This is generally a good practice, but this is a good place to repeat it. + + diff --git a/src/content/docs/getting-started/glossary.mdx b/src/content/docs/getting-started/glossary.mdx index 757b7f4..64a59e4 100644 --- a/src/content/docs/getting-started/glossary.mdx +++ b/src/content/docs/getting-started/glossary.mdx @@ -12,6 +12,8 @@ jsonLd: publisher: { "@id": "$organizationId" } --- +import ClapButton from "../../../components/ClapButton.astro"; + Before we start, let us introduce a few terms that we will use a lot: - **Model**: A particular LLM, like Claude-4.6-Opus, GPT-5.3-Codex, Gemini-3.1-Pro. @@ -34,3 +36,5 @@ Before we start, let us introduce a few terms that we will use a lot: - **Gate**: A check that work must pass before it can move forward. The term predates AI agents, but agentic workflows made it much more common because they require explicit checkpoints for reviewing and verifying autonomous work. In practice, a gate can be a lint run, typecheck, test suite, code review, preview deployment, or any other requirement that blocks changes until they meet your quality bar. + + diff --git a/src/content/docs/getting-started/how-to-get-started.mdx b/src/content/docs/getting-started/how-to-get-started.mdx index c8be3eb..1265ec9 100644 --- a/src/content/docs/getting-started/how-to-get-started.mdx +++ b/src/content/docs/getting-started/how-to-get-started.mdx @@ -5,6 +5,8 @@ description: >- learning path to take first. --- +import ClapButton from "../../../components/ClapButton.astro"; + This "Getting Started" chapter is here to give you a concrete sense of what is possible with agentic engineering. @@ -48,6 +50,8 @@ That is how you begin to build intuition. And once you have a bit of real experience, the rest of this book will become much more useful. + + ## Two practical paths Because hands-on work matters so much, this chapter is organized around two @@ -84,3 +88,5 @@ top of it at the same time. For this path, feel free to jump to [First steps in mature projects](/getting-started/first-steps-in-mature-projects/). + + diff --git a/src/content/docs/getting-started/how-to-set-up-a-new-repo.mdx b/src/content/docs/getting-started/how-to-set-up-a-new-repo.mdx index 6161a68..86d0c7a 100644 --- a/src/content/docs/getting-started/how-to-set-up-a-new-repo.mdx +++ b/src/content/docs/getting-started/how-to-set-up-a-new-repo.mdx @@ -3,6 +3,8 @@ title: How to set up a new repo? description: Step-by-step setup for starting a new repository with coding agents, from discovery and planning to review and first commit. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; import { Steps } from "@astrojs/starlight/components"; @@ -26,6 +28,8 @@ perspective this thing should just happen in background and have no influence over what input/output devices does user set. write me a complete poc ``` + + ## A first commit in 8 steps @@ -47,6 +51,8 @@ over what input/output devices does user set. write me a complete poc Here is an example conversation where the author started building a desktop app (used Amp for its thread-sharing feature; used a GPT model to pack more prompts into a single thread, just so it’d be easier for you to read). Notice how gibberish such a conversation can be! Prompts can be misformatted and full of typos. LLMs are very capable of ignoring this noise! Notice how much of this thread is just questions or “do whatever you want” answers. + + ## A first bug fixed in 7 steps :::note @@ -74,6 +80,8 @@ With Debug Mode, instead of guessing, the agent can form clear hypotheses, add i + + ## A first design implemented in 4 steps With the right tools, agents are excellent at turning Figma designs into rough code. If you’re building a web or mobile app, let’s try this. @@ -94,3 +102,5 @@ That’s it! The output code will very likely be a mess because you probably hav If you’re curious, also check out: - + + diff --git a/src/content/docs/getting-started/towards-self-improvement.mdx b/src/content/docs/getting-started/towards-self-improvement.mdx index 6926bb8..93a6954 100644 --- a/src/content/docs/getting-started/towards-self-improvement.mdx +++ b/src/content/docs/getting-started/towards-self-improvement.mdx @@ -3,6 +3,8 @@ title: Towards self-improvement description: Start adapting your repository to coding agents with a minimal `AGENTS.md` and a few simple setup conventions. --- +import ClapButton from "../../../components/ClapButton.astro"; + import ExternalLink from "../../../components/ExternalLink.astro"; import { Steps, TabItem, Tabs } from "@astrojs/starlight/components"; @@ -91,6 +93,8 @@ or Cursor Rules + + ## More utilities await `AGENTS.md` is the simplest place to start, because it gives you immediate @@ -109,3 +113,5 @@ useful once you already have a stable basic workflow. When you are ready, continue with [Harness engineering](/becoming-productive/harness-engineering/), which covers these more advanced building blocks in detail. + + diff --git a/src/content/docs/getting-started/what-can-ai-agents-even-do.mdx b/src/content/docs/getting-started/what-can-ai-agents-even-do.mdx index a78f43d..b1a3843 100644 --- a/src/content/docs/getting-started/what-can-ai-agents-even-do.mdx +++ b/src/content/docs/getting-started/what-can-ai-agents-even-do.mdx @@ -3,6 +3,8 @@ title: What can AI agents even do? description: A quick capability checklist of what modern coding agents can do across code navigation, debugging, planning, and automation. --- +import ClapButton from "../../../components/ClapButton.astro"; + - Index, understand, and navigate your codebase by themselves. - Search the internet. - Connect to external services (see MCP, etc.). @@ -10,3 +12,5 @@ description: A quick capability checklist of what modern coding agents can do ac - Prepare an implementation plan for you. - Read and analyze screenshots, videos, and even Figma designs. - Automatically test changes (for example, in your browser!). + + diff --git a/src/content/docs/index.mdx b/src/content/docs/index.mdx index 51e1a59..7613d94 100644 --- a/src/content/docs/index.mdx +++ b/src/content/docs/index.mdx @@ -3,6 +3,8 @@ title: Welcome to the Software Mansion Agentic Engineering Guide! description: Practical guidance for setting up and scaling agentic engineering workflows in real software projects. --- +import ClapButton from "../../components/ClapButton.astro"; + import ExternalLink from "../../components/ExternalLink.astro"; This book collects practical insights from applying agentic engineering patterns in Software Mansion's own projects and in our clients' work. We are sharing it publicly so more teams can build with these methods. @@ -22,6 +24,8 @@ What makes it engineering, rather than just vibe coding, is the standard of work This guide is about that professional layer: how to set up the environment around agents, how to collaborate with them effectively, and how to keep code quality under control as their role in the workflow grows. + + ## Learning paths If you are short on time, use the learning paths below. @@ -30,6 +34,8 @@ If you are short on time, use the learning paths below. - **Already experienced**: Skim [Getting Started][chapter-getting-started], read [Becoming Productive][chapter-becoming-productive] in full, then jump to selected sections in [Expanding Horizons][chapter-expanding-horizons]. + + ## Chapters This guide is divided into three main chapters. Each chapter increases the level of agentic initiation @@ -61,3 +67,5 @@ This guide is divided into three main chapters. Each chapter increases the level [chapter-getting-started]: ./getting-started/how-to-get-started/ [chapter-becoming-productive]: ./becoming-productive/the-workflow/ [chapter-expanding-horizons]: ./expanding-horizons/threads-context-and-caching/ + +