The request asks for a tool to optimize business processes. Among the candidates, Pipefy (its AI agents for workflow automation) and Anthropic (its process-optimization skill for analyzing and improving business processes) most directly match, with Pipefy's process-intelligence skill explicitly analyzing pipes for bottlenecks and automation gaps 71711.
- 1
Anthropicanthropic.comverified and signed
Its process-optimization skill analyzes and improves business processes, triggered by requests such as 'this process is slow' or 'streamline this workflow' 11.
+68 community tools built for it
for agents: process-optimization · process-doc · process-letter
- 2
Pipefypipefy.comverified and signed
Its pipefy-process-intelligence skill analyzes an existing pipe for automation gaps, manual bottlenecks and missing steps to improve the workflow 17, and its AI agents automate workflows to cut manual work 7.
+3 community tools built for it
for agents: pipefy-process-intelligence · pipefy-process-design · pipefy-ipaas
Sources
- 1Home \ Anthropicanthropic.com · read 2026-10-29
- 7Pipefy: AI Agents for Workflow Automationpipefy.com · read 2026-10-30
- 11process-optimization: declares "process-optimization" (the record we read and signed)unfragile.ai · read 2026-10-24
- 17pipefy-process-intelligence: declares "pipefy-process-intelligence" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
process-optimization · process-optimization verified and signed
Analyze and improve business processes. Trigger with "this process is slow", "how can we improve", "streamline this workflow", "too many steps", "bottleneck", or when the user describes an inefficient process they want to fix.
docker-build-strategies · docker-build-strategies verified and signed
Use this skill when writing, reviewing, or optimizing Dockerfiles, even if the user just says their image is too large, their build is slow, or they need to harden a container for production. Covers multi-stage builds, layer caching, .dockerignore, non-root users, and image size optimization.
vercel-optimize · vercel-optimize verified and signed
Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verifi
arize-prompt-optimization · arize-prompt-optimization verified and signed
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond bette
web-perf · web-perf verified and signed
Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.
agents-optimize · agents-optimize verified and signed
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "redu
pipefy-process-intelligence · pipefy-process-intelligence verified and signed
Use this skill when the user wants to analyze an existing pipe for improvement opportunities — automation gaps, manual bottlenecks, missing AI agents, field conditions, or adjacent processes. Acts as a process analyst: investigates, diagnoses, and improves the pipe in progressive rounds — each round
prompt-optimizer · prompt-optimizer verified and signed
Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, o
insert_rows · MySQL (Activepieces) verified and signed
Insert Multiple Rows — Inserts many rows into a table in a single transaction
createPipelineForRepository · Bitbucket API verified and signed
Run a pipeline
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.