A developer built PlannerCritic, an open-source engine in which one LLM drafts a plan, a second LLM reviews it, and deterministic gates decide whether it can proceed, then ran it against 170 real chan…
A developer's LLM-based plan critic returned a different verdict on every trial of identical input, yet never let a defective plan through, because deterministic gates and a code-enforced allowlist, n…
A developer built two LLM-based systems, PlannerCritic and AdversarialDebate, to detect when an LLM's judgment is wrong. Both systems proved reliable but shared a blind spot: their safety metrics impr…
A public audit of the v0.2.1 release of the PlannerCritic engine found that three of five frozen claims were contradicted by public artifacts, including a test count discrepancy (1294 passed, 1 failed…
An engineer's attempt to prompt-inject their own open-source agent engine, PlannerCritic, failed across three releases. The engine's architecture, not its prompts, blocked direct injection attempts, i…
An engineer's field test of the open-source PlannerCritic engine, which uses one LLM to write plans and a second to review them, found 10 issues across 157 goals for $0.30 in v0.1.0, including a true …
An engineer building PlannerCritic, an open-source engine where one LLM writes a plan and a second reviews it, found that the planner consistently makes three structural mistakes—unverified dependenci…
A developer building PlannerCritic, an open-source engine where one LLM writes a plan and a second reviews it, found that an adversarial critic prompt caused the reviewer to block plans for completene…
A developer built PlannerCritic, a system that treats an AI agent's plan like a pull request, using one LLM to draft and another to review before execution. Field tests with 157 agent plans revealed t…