Week 5 of 8 · Use AI + Build AI

The SDLC at scale, frameworks, providers and evals

The workflow upgrade first: 3 CLIs, a shared context architecture, 50 concurrent agents. Then the agent on 3 frameworks and 2 providers, with evals as the gate for everything that follows.

What the week builds toward

The workflow upgraded to 3 CLIs and a 50-task fleet through the backlog, the investigation agent rebuilt on a chosen framework, WorkBot running on 2 providers with routing and fallbacks, and an eval suite gating every pull request.

The 5 days

  1. Day 21

    Multi-CLI development and context architecture

    Claude Code, Codex CLI and OpenCode on one shared policy, and the context an agent gets: company brain plus per-task brief.

    You ship: An agentic development setup across 3 CLIs, a company brain, and a one-page guide.

  2. Day 22

    Agent fleets: 50 concurrent agents, cloud agents and test automation

    50 specified tasks dispatched across worktrees and cloud agents, with a review fleet and a merge queue.

    You ship: A 50-task fleet run measured on merges per hour, reverts and brief-to-merge time.

  3. Day 23

    Agent frameworks: LangGraph.js, Claude Agent SDK, OpenAI Agents SDK

    The same research agent on 3 frameworks, with a written tradeoff.

    You ship: The Day 11 research agent on 3 frameworks, measured on 5 topics, with a one-page comparison.

  4. Day 24

    2 providers, 1 codebase

    One provider layer, per-task routing with fallbacks, and evals that decide the routing.

    You ship: WorkBot's web chat on OpenAI and Anthropic with a routing table, fallbacks and eval scores for both.

  5. Day 25

    Evals as the development loop

    Eval sets, calibrated judges, variance-aware thresholds, and evals as a CI merge gate.

    You ship: WorkBot on the chosen framework and 2 providers, developed with the fleet workflow, gated by evals in CI.