Skip to content

docs: position Decision Engine as a portfolio product #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Masterleeaus merged 1 commit into from
Oct 4, 2026
Merged

docs: position Decision Engine as a portfolio product #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,19 +16,20 @@
<a href="#architecture">Architecture</a> ·
<a href="#capabilities">Capabilities</a> ·
<a href="#trust-boundaries">Trust boundaries</a> ·
<a href="#see-it-in-action">Demo</a> ·
<a href="#reproducible-authority-handoff-evaluation">Authority eval</a> ·
<a href="#implementation-status">Implementation status</a>
</p>

---

## Make the path to a decision visible
## Decision intelligence that stays explainable

A single score can hide missing evidence, policy limits, competing objectives, or fragile assumptions. Titan separates those concerns into explicit stages so a reviewer can see what is known, what remains uncertain, which options are eligible, why one leads, and what approval is still required.
Teams make consequential choices with evidence scattered across systems, objectives pulling in different directions, and policy or approval requirements that are easy to lose in a score. Titan Decision Engine turns those inputs into a decision path that a reviewer can inspect from source evidence to recommendation.

**Titan Decision Engine** is a modular decision-support layer for AI-assisted and human-reviewed systems. It is designed for business, operational, workforce, environmental, financial, procurement, scheduling, and other decision domains.
**For product and platform teams**, it is a modular TypeScript decision layer for operational, workforce, financial, procurement, scheduling, environmental, and other AI-assisted workflows. It preserves evidence, uncertainty, constraints, trade-offs, provenance, and confidence so the next action is easier to evaluate and govern.

> **Decision model:** subject + objectives + options + evidence + constraints + preferences → predicted outcomes and trade-offs → ranking → recommendation + confidence + authority requirements.
> **Value proposition:** turn complex evidence into constraint-aware recommendations with a clear boundary between analysis, host approval, and execution.

The engine can analyze and recommend. It does not authorize or execute the recommendation.

Expand All @@ -46,6 +47,10 @@ npm run example:environment

`npm test` builds the package entry point and all 21 engine projects, then runs the 16 compiled TypeScript suites and five JavaScript suites. `npm run build` builds without running tests. `npm run coverage` runs the same tests through c8. The package exposes the engines through named namespaces at its root and stable subpath exports.

## See it in action

The [deterministic authority-gate demo](docs/authority-gate-demo.md) runs without credentials and exercises the implemented Step 27 handoff with three synthetic outcomes: an eligible recommendation is prepared, an ineligible recommendation is blocked, and an approval-required request remains undispatched. It is a compact way to see the engine's authority boundary before reading the full evaluation.

## Architecture

<p align="center">
Expand Down
Loading