Talk submission: Declan Johnston

[github-actions]

Submitted via #31 by @declanatinference.

Field	Value
Speaker	Declan Johnston
Startup	https://inference.net
Repo	https://github.com/context-labs/HALO

A general-purpose harness like Claude Code is the wrong tool for trace analysis. This isn’t because the model isn’t smart, but because traces can get extremely long, and you need a specialized toolkit in order to make observations about systemic agentic behavior. HALO (Hierarchical Agent Loop Optimization) is a methodology for building recursively self-improving agent harnesses using RLMs.

The core HALO loop is suprisingly simple:

1. Collect execution traces from your agent harness. HALO uses OpenTelemetry-compatible tracing.
2. Feed traces into HALO-RLM engine.

---

🛠️ Auto-corrections applied (organizer can edit on this branch before merging):

• Summary trimmed from 922 → 572 chars at sentence boundary. Full text stays on HALO: Build recursively self-improving agents #31 — the homepage links back via […].

---

Approve = merge this PR (closes #31 and rebuilds the homepage). Reject = close this PR with a brief comment. Edit before approving: push commits to talk/31 (e.g. fix a typo in the summary), then merge.

Closes #31