PACE Framework

What is PACE?

PACE (Plan · Architect · Code · Evaluate) is an AI-driven sprint execution framework. Instead of one monolithic AI generating an entire feature, PACE runs a structured team of six specialised agents that mirror the roles of a real engineering squad:

PRIME — Planning

Reads your sprint plan and generates a daily Story Card with user stories, acceptance criteria, and scope boundaries.

FORGE — Implementation

Writes production code using a tool-calling loop. Follows TDD, respects source directory boundaries, and produces a Handoff Note.

GATE — Quality

Runs your test suite, checks CI results, and evaluates every acceptance criterion. Issues SHIP, HOLD, or PARTIAL decisions.

SENTINEL — Security & SRE

Scans for hardcoded secrets, input validation gaps, missing timeouts, and unhandled error paths.

CONDUIT — DevOps

Reviews CI/CD workflows, Makefile targets, dependency lock files, and deployment configuration.

SCRIBE — Documentation

Keeps your context documents, README, and engineering docs in sync with what was actually built each day.

Why PACE?

Most AI coding assistants work in isolation — they write code but can’t run your tests, review CI, or check for leaked credentials. PACE closes that loop:

• Structured handoffs: every agent reads the previous agent’s output, creating a verifiable chain of evidence.
• Blocking gates: a failing test or exploitable vulnerability stops the day before code ships.
• Advisory backlog: non-blocking findings accumulate and are force-cleared on dedicated review days.
• Platform-agnostic: GitHub, GitLab, Bitbucket, Jenkins, or fully local.
• LLM-agnostic: Claude, GPT-4o, Gemini, Bedrock, Ollama, Groq, and any LiteLLM-supported model.
• Token-efficient by design: stateless agents with bounded, purpose-built context — not one monolithic session accumulating history. A full pipeline run costs $1.50–3.00. A 30-day sprint runs ~$60–90 total.
• Complete cost transparency: PROGRESS.md tracks per-story actual cost, retry waste, and running sprint total — the only AI framework that tells you exactly what you spent and what was wasted.

For solo founders and small teams

PACE is an always-on engineering pipeline at the cost of a SaaS subscription. While you focus on product decisions, PACE runs the daily implementation loop: writing production code, running your test suite, catching security issues, reviewing CI, and updating your documentation. Human review happens at designated gate days — not on every step.

A typical 30-story sprint — complete with tests, security reviews, and DevOps checks on every story — costs $60–90 in API usage. No headcount. No context-switching. Full audit trail.

Explore the Docs

Quickstart Get PACE running against your repo in under 10 minutes.

Your First Sprint End-to-end walkthrough of a 5-day PACE sprint.

The PACE Pipeline Understand how the six agents connect day by day.

pace.config.yaml Reference Every configuration field explained with examples.