Boxdawn
01/proven / not yet

What's proven. What's not.

Most tools hide this section. We think it is the product.

Proven
  • The problem is real. Token cost is a top operational pain in multi-agent systems, and the waste sits between agents, not inside them. (public market data, sources linked)
  • External evidence the problem exists. F1 0.72 on 1,575 LangGraph agent traces — hybrid method, unrelated implementation (arXiv:2511.10650).
Not yet
  • Real-world semantic separation. In our real-data probes, the zero-false-positive result came from the structural layer; the semantic layer did not cleanly separate same-topic outputs. We published this finding instead of hiding it.
  • Measured savings. We have not yet measured a single dollar saved in production. No user count, no testimonials — because there are none yet.

When something moves from the right column to the left, you'll read it here first.

02/reports

Reports

Reports published under the previous product name Clew. Boxdawn is the same product, renamed 2026-08.

2026-08

Waste-rate replicates across coding and non-coding agents

Claude Code (28 sessions) · Toolathlon (6,780 trajectories · 22 models)GO

Union of 4 deterministic detectors reports 99.3% WR_char on 28 Claude Code sessions and 93.4% WR_char on 6,780 Toolathlon trajectories (22 frontier models). Same pattern, structurally distinct corpora — coding sessions and non-coding tool-use tasks.

2026-08

Toolathlon adapter unblocked via pre-registered amendment

Toolathlon (6,780 trajectories · 22 models)GO

August 10 scan excluded 100% of trajectories due to an adapter gap. Amendment prereg (docs/WASTE_RATE_TOOLATHLON_ADAPTER_AMENDMENT_PREREG.md) locked reconstruction rules and prediction bands on August 11 before any code landed. Re-scan produced 4/4 measurable prediction passes with no post-hoc adjustment.

2026-07

A pattern we implemented but never saw

Claude Code · Toolathlon · RedundancyBenchN/A

One of the three detected patterns has never fired on real data. We label it as such rather than advertising it.

2026-07

The re-read detector we killed

Claude Code sessionsKILL

Hand-labeled 30 pairs. Precision 0–3.3% against a pre-registered threshold of 0.70. Detector descoped from Clew.

Boxdawn diagnoses; it does not fix. No measured cost savings yet — we report what was found, not what was saved.