USE SOTA SERVICES
IN YOUR OWN PROJECTS.

UX critique + pitch-deck critique + multi-stage user-flow critique engine — graph-backed expert that classifies the domain, applies the relevant pattern library, and produces structured critiques where every claim cites a specific graph node. v=11 NEW (2026-05-13): two improvements addressing 'the Lambda has no deck-level context' question. (1) Taxonomy expansion: added `wedge` (defensibility / 'why our angle is unique' — distinct from `competition` 2x2/vs-table) and `why_now` (timing/inflection argument — distinct from `market_size` TAM math). Lets the classifier distinguish slides 4 (Wedge) from 5 (Market Map) and slides 6 (Why Now) from 7 (Market Math) in a typical seed deck. (2) Deck-level context preamble in the Pattern A batch prompt: each batch now ships a `--- DECK CONTEXT ---` block with deck identity, audience tier, total slide count, full slide arc (all slides, not just batch), and expected-vs-missing slide types for that audience. Subagent can now catch deck-level gaps (e.g. 'no team slide on a seed deck — partner will probe') instead of critiquing each slide in isolation. v=10 changes (sub_shape match, section_divider exclusion, critique-may-be-empty) preserved. v=9 visual comparator wiring preserved. v=10 NEW (2026-05-13): three fixes from the v=9 self-tests against CareerGraph V1 + Lago. (1) sub_shape layout matching — each gold-deck slide now carries a sub_shape tag (~22 categories: section_divider, hero_with_logo, competition_matrix_2x2, competition_vs_table, traction_growth_curve, traction_logo_wall, market_size_circles, market_size_bar, ask_milestone_columns, ...). The selector matches (audience, classification, sub_shape) where sub_shape is a strong tiebreak — shape-matched comparators always win over shape-mismatched ones within the same classification. Closes the Lago s12 / CareerGraph s5 bug where a 2x2 positioning slide got paired with an iPhone-screenshot 'competition' slide. (2) section_divider exclusion — divider exemplars are never surfaced as comparators (Lago self-test showed dividers paired with content slides as pure noise). (3) fault-finding bias fix — the per-slide schema now allows critique:[] and adds optional strengths_observed:[] so subagents on canonical-quality slides can say 'this is well-anchored' instead of forced filler bullets. The v=9 visual comparator wiring (65-exemplar gold-deck corpus) is preserved. v=8 user_complaint + v=8.1 citation-strict preserved. v=7 critique_flow (alpha) preserved. v5 record_feedback MCP tool preserved. v4 deferred items preserved.

Spec-conformance auditor — reads a spec, runs a repo against it, reports drift

Python CLI + library for site crawling, markdown extraction, screenshot capture, and page classification. v3 closes 3 unresolved v2 feedback items: (1) bug fe6f3c39 — binary missing flags (root cause was stale local install; PyPI 0.9.3+ already had them; v0.10.0 + CI smoke job + README upgrade docs prevent regression); (2) perf c69402e7 — replaced uncapped doubling-from-1s (the actual bug; 'fixed 60s' was misremembered) with tenacity full-jitter 2s→30s 5-attempts; (3) works_well a179496d — designlens consumers can stop using Playwright fallback after `pip install --upgrade markcrawl`. v3 also adds: ERROR-severity terminal-failure logs with URL extraction, before_sleep retry observability, CI workflow catching source-vs-PyPI drift.

Class A SOTA container for Supabase migration drift prevention + resolution across multi-repo → single-DB setups. Wraps the Supabase CLI with a coord-locked pre-push gate (`protect`) and a 17-probe DDL classifier emitting proposed actions (`resolve --dry-run|--consensus-review|--apply`). Library + CLI + MCP surfaces. Loose-pin depends on @id8/coord for cross-session advisory locks.

v=5 ships --dangerously-skip-permissions / --yolo CLI aliases + slash command YOLO mode for end-to-end pause-free autonomous runs (mirrors Claude Code's harness flag of same name). Hard floors remain non-bypassable (Phase 4 hard-floor, Ralph Loop check, server timeout, rubric tripwires).