The Orchestration Guide
Step-by-step, plain-English orchestration playbook: when not to orchestrate, the one-fast-lane rule, receipts over raw output, and keeping the planner's cache warm. Experience-based — no control study yet.
Read the guidePUBLICATION INDEX
Research, with receipts.
Methods, postmortems, and live research questions from the Gaia laboratory. Every finding names its evidence; every unfinished study says so plainly.
Research publications
Context Diet
Local token-budget estimator; comparative benchmark results pending review.
Play Context DietThe Compounding Cost of CI Failures
Postmortem of Epic #780 introducing CI Churn as a first-class cost metric.
Read the postmortemWhen Agents Report Their Own Cost
Proposed study of the gap between agent estimates, rate-card totals, and invoices.
Read the planGaia MCP
Model Context Protocol server exposing the Gaia Skill Tree to Claude Code, Codex, and Cursor.
Learn moreParallel Cheap-Scout Fan-Out Benchmark
Empirical study of parallel cheap-scout fan-out vs single mid-tier scouts across 360 runs: Pareto frontier, prompt-cache amplification, and flake rate reduction.
Read the benchmark & receiptsThe Hell Heaven Benchmark
Drug-trial method for scoring skills by marginal efficacy against model baselines. Arc I verified: baseline floor pricing, census, and machine-gated claim index.
Read the benchmark & receiptsContext Compaction Phase 2 Empirical Benchmark
Empirical study across 37 live agent sessions (25 across S1/S2/S4/S6 + 12 across S3) and 8 autocompaction thresholds on Gemini 3.8 Flash: Pareto frontier, prompt-cache amplification, reacquisition thrashing, and super-linear reasoning scaling.
Read the methodology & receipts