Results for “agents”

Ultra-Sharp Agent Skills — a research-first skill-authoring system + 72 production-ready skills for AI agents.

Agentic web research engine — hypotheses, verbatim evidence, contradictions, sourced answers streamed live. Claude Opus 5 + Firecrawl + PostgreSQL.

chat-spboucher-ai · main

phi-conseil · main

uqo-eval · main

vrai-prix · main

toveli · main

maclustr-console · main

worthdoing · main

valoplex · main

wp26_uqo · main

autoscholar · main

internetpressure · main

company-atlas · main

satelliteindex · main

rareindex · main

countryatlas · main

doc-api · main

doc-api · main

groupe-ka · main

groupe-ka · main

doc-api · main

wpai0002_uqo · b4b5fe4 · Simon-Pierre Boucher · 8 h ago

wp26_uqo · b780d9e · Simon-Pierre Boucher · 12 days ago

wp27_uqo · 7377aa2 · Simon-Pierre Boucher · 13 days ago

…lls A research first skill authoring system + 72 production ready skills for AI agents Every skill: a trigger optimized description, one default per decision, a validation loop workflow, and pairwise exclusive boundaries…

…a knowledge graph with AI suggested links, a research workspace, controlled AI agents and encrypted backups — on one PostgreSQL, served from a Mac Studio of the MacLustr cluster through the MacLustr Tunnel. Contents Fea…

…te Collar Worker Measuring the economic frontier of Claude Code, computer using agents and autonomous knowledge work. UQO Working Paper Series No. 42 (Department of Administrative Sciences, Université du Québec en Outaou…

…version 1.1) — Measuring 22 ways of passing information between language model agents (text, summaries, structured evidence, quantized and evicted KV caches) on Qwen2.5 3B and Llama 3.2 3B over 13,280 trials with measur…

….944, and the null is unchanged 📄 Abstract Instruction files that steer coding agents through research tasks range from one sentence to several thousand words of phases, gates and integrity rules. We ask whether that st…

…Machines UQO Working Paper No. 27 — Price Discovery in Markets Populated by LLM Agents b31b1b?logo=latex&logoColor=white) TL;DR — An event sourced limit order book exchange with exact accounting and a latent dividend pro…

…(2021–2026) testing whether debate among twelve role specialised LLM valuation agents adds information: debate reaches a mean absolute log error of 0.158 against 0.159 for the same agents kept silent, and every preregis…

📈 In one sentence — Delegating decisions to agents built on shared foundation models turns idiosyncratic error into common model noise: closed form loadings in the delegation share and number of models, a zero private–s…

…is under represented. Screening and extraction were performed by language model agents whose model version and decoding settings were not logged; the duplicate extractor and the re reader are of the same model family, an…

…fficients are predictive associations: listing content is chosen by sellers and agents, and the three visual quality scores are collinear enough that only their joint contribution is well identified. There is no human la…

…. Supervision — connecteurs surveillés par les gardiens autonomes du Groupe KA (agents ka6, supervision api ka) ; expose le et les boutiques désactivées. Visite guidée 10 captures du site en production (2026 08 28, deskt…

…, invariants (uid uniques, URLs absolues, salaires plausibles). Supervision par agents gardiens — les connecteurs sont surveillés en continu (gardien ka6) : chaque panne de source est diagnostiquée (panne externe vs bug)…

…contrôle publique — pages (disponibilité de 19 cibles : les 16 sites d' + les 3 agents gardiens ka2.bot/ka4.bot/ka6.bot, historique 90 jours, ticks aux 5 min) et (tableau de bord maître consolidé). Pour qui ? Les visiteu…

…tion (up to 750 pages), intelligent crawling, structured extraction, autonomous agents Exa Semantic neural search, content retrieval, similar page discovery SerpAPI Google Search, Images, Shopping, Finance, Trends, Schol…

…ès coupure) → boot → ouverture de session automatique ( + , posés par ) → LaunchAgents ( → , gardiens, pousseur) + LaunchDaemons ( , PM2 en daemon sur M2U64 et les nœuds loués) → apps up → route Caddy inchangée sur BHS64…

…026 09 18/19 : models, endpoints, parameters, objects, streaming events, tools, agents, realtime, media, files, batch, fine tuning, evals, admin, pricing, rate limits, errors, headers, SDKs, security, and a multi provide…

KA Guardian — ka2 · ka4 · ka6 Les trois agents gardiens autonomes du Groupe KA. Un seul repo, trois instances, trois salles de contrôle publiques : www.ka2.bot · www.ka4.bot · www.ka6.bot Depuis le 2026 08 23, ka2/ka4/ka…

…bKit , with deterministic, testable extraction. 🌐 Live · ▶ Playground · 🤖 For agents · 📖 Docs · 📦 Source ✦ Why Tendril Firecrawl runs in the cloud, on datacenter IPs, in headless Chromium. Tendril runs on a residenti…

…e, generations, usage, model catalog cache, sessions Supervision: three launchd agents ( , , nightly at 03:30 with 14 day retention) Local development Deployment (m4m64a) launchd agent Role on port 3000, KeepAlive , Keep…

…llie, agences québécoises, Gala InfluenceCréation…). 3. Extraction structurée — agents parallèles → JSON normalisé par source. 4. Fusion/déduplication ( ) — clé nom normalisé + alias + handle, valeur max par métrique, fi…