Skip to content

epic: AI agent optimization — 23 workstreams #211

@JeffOtano

Description

@JeffOtano

Status update (2026-05-12 UTC): Refreshed against current GitHub issue state. #190, #198, #199, #215, and #216 are now closed, so the remaining open items should be prioritized from current code evidence and telemetry.

Tracks 28 optimization workstreams identified in the April 2026 AI agent audit + world-class best-practices research. Sources cited inline in each child issue.

Sequencing update (2026-04-17): telemetry + eval move to the front. Don't optimize prompts further without a way to measure. Build the scoreboard first.

TL;DR — expected impact

  • Cost: 60-80% input-token reduction on active chat sessions once cache restructuring ships; another 60-80% on chitchat once intent routing ships.
  • Latency: cache hits cut TTFT by up to 85%; hedged requests eliminate failover penalty during outages.
  • Quality: production agent-eval (tool choice, args, end-state, multi-trial) + A/B framework replaces ship-blind prompt edits with measurable iteration.
  • Reliability: circuit breaker handles 99-99.5% LLM uptime reality; budget cap protects BYOK users from runaway loops.

Phase 0 — build the scoreboard first

Ship nothing downstream until we can measure what it did.

Phase 1 — architectural reshape

Biggest structural wins. Do these before touching prompts further.

Phase 2 — cache restructuring

Unblocked once #192 and #216 land.

Phase 3 — routing + tool surface

With the scoreboard live, now safe to tune.

Phase 4 — reliability

Phase 5 — quality systems + memory

Parking lot — do after data

Key dependencies

References

Metadata

Metadata

Assignees

No one assigned

    Labels

    ai-agentWork on the AI coach agent systempriority: criticalHighest priority work

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions