Playbooks · Agent workflows
Carry approved working memory into the next run
Persist reusable project facts outside the conversation and retrieve only relevant notes on a later run.
FREE AGENT SKILLS · MCP · AUTOMATION
Playbooks
Free public resources
Agent artifactsAgent authorizationAgent contextAgent evaluationAgent interoperabilityAgent memoryAgent observabilityAgent operationsAgent orchestrationAgent outputAgent recoveryAgent reliabilityAgent researchAgent runtimeAgent safetyAgent setupAgent stateAgent toolsAgent workflowsContent automationCrypto quant researchCrypto quant workflowsData automationDocument automationDocument and data automationMCP clientsMCP reliabilityMCP resourcesMCP serversMCP testingRetrievalSkill authoring
Playbooks · Agent workflows
Compact context automatically during long research sessions
Configure Managed Agents to summarize older turns near the context threshold so the agent can continue incorporating new evidence.
Playbooks · Agent workflows
Summarize session memory at task milestones
Create compact carry-forward summaries at explicit milestones so work can continue without replaying every turn.
Playbooks · Agent workflows
Continue a response stopped by the output limit
Detect `max_tokens` termination and continue generation without duplicating or silently truncating the result.
Playbooks · Document and data automation
Prepare interview questions from a recording
Transcribe an authorized recording with Deepgram, then ask Claude to draft open-ended interview questions from the transcript.
Playbooks · Agent workflows
Summarize approved web pages for a brief
Fetch a bounded set of approved pages, extract readable text, and produce a concise summary with source links.
Playbooks · Agent workflows
Cache stable instructions across repeated requests
Reduce repeated prompt cost by placing stable instructions and reference material in a cacheable prefix.
Playbooks · Agent workflows
Prewarm research context while the user types
When a user begins composing a query, send a one-token request with the same large context to hide cache-creation latency.
Playbooks · Agent workflows
Browse, organize, and branch agent sessions
List local session history, read messages, add titles/tags, and resume a branch from an earlier conversation while preserving the original.
Playbooks · Agent workflows
Review fraud cases with multiple MongoDB Atlas signals
Combine vector, full-text, hybrid-ranking, and graph retrieval to prepare an evidence-backed review of a pending transaction.
Playbooks · Agent workflows
Remember preferences in a per-customer memory store
Attach a customer-scoped memory store to sessions so approved preferences persist across visits without mixing tenants.
Playbooks · Agent workflows
Triage memory-safety findings in source code
Establish authorized scope and a threat model, then use read-only agents to discover and independently verify memory-safety issues in C code.
Playbooks · Agent workflows
Turn an incident alert into a reviewable fix
Use an incident payload to investigate logs and configuration, then prepare a pull request that waits for human approval.
Playbooks · Agent workflows
Fact-check a multi-claim document with verifier workers
Route individual claims from a draft to independent source-checking workers and require structured verdicts before producing a corrected report.
Playbooks · Agent workflows
Turn long reports into verifiable executive briefs
Produce a short brief of a long report with key claims and source locations for executive review.
Playbooks · Agent workflows
Turn a team inbox into a daily action brief
Read approved email and calendar data and organize tasks and meeting preparation by urgency.
Playbooks · Agent workflows
Escalate difficult decisions to an advisor model
Let a regular agent handle tasks and consult a stronger model only on explicit triggers, retaining the rationale.
Playbooks · Agent workflows
Route high-risk expenses for manager approval
Process expense events; let rules handle low-value claims and pause high-risk claims for a manager decision.
Playbooks · Agent workflows
Diagnose recurring defects in production agent answers
Find recurring defects in agent conversations stored in BigQuery and produce evidence-backed improvement leads.
Playbooks · Agent workflows
Generate a cited, brand-aligned presentation
Review research and a brief first, then generate a branded PowerPoint draft with speaker citations.
Playbooks · Agent workflows
Answer shopping needs with semantic catalog search
Map natural-language shopping needs to BigQuery attributes and Vector Search results, returning verifiable product candidates.
Playbooks · Agent workflows
Recover zero-result retail searches and improve titles
Mine high-intent terms from BigQuery, inspect zero-result queries, and create explainable title recommendations.
Playbooks · Agent workflows
Generate a quality-checked virtual try-on product clip
Generate a VTO/R2V clip from authorized model and product images, then check rotation consistency and artifacts.
Playbooks · Agent workflows
Assemble a small-business loan file for human review
Chain application extraction, eligibility checks, risk review, and evidence validation into a loan file for review.
Playbooks · Agent workflows
Prepare an account brief for an upcoming customer meeting
Combine account notes, feedback, product usage, and news into a meeting brief and agenda on a schedule.
No matching entries.