🧠 AI & Machine Learning · Flowchart
AI Agent Tool-Use Workflow
How an AI agent completes a task by planning, calling tools, checking results and asking a person to approve risky actions before it finishes.
Drawing diagram…
What this diagram shows
- The agent loops until the goal is met or a step limit is reached
- Actions that change data need human approval
- Every tool call is logged for review
Prompt used
Flowchart of an AI agent: it receives a task, makes a plan, picks the next tool (search, database query, API call or code run), runs it and checks the result. If the next action changes data or spends money it asks a human to approve. It repeats until the goal is met or it reaches 15 steps, then writes a summary. Every step is logged.
Mermaid code
flowchart TD
A[Receive task] --> B[Make a plan]
B --> C[Choose next tool]
C --> D{Changes data or spends money?}
D -->|Yes| E[Ask a person to approve]
E -->|Rejected| B
E -->|Approved| F[Run tool]
D -->|No| F
F --> G[Log the call and result]
G --> H{Goal met?}
H -->|Yes| S[Write summary for the user]
H -->|No| I{Step limit of 15 reached?}
I -->|No| C
I -->|Yes| J[Stop and report what is left]Related templates
RAG Chatbot over Company Documents
A chatbot that answers staff questions from company documents: documents are split and indexed in a vector database, and each question pulls the most relevant passages before the language model writes an answer.
RAG Question Answering Sequence
What happens when a user asks the document chatbot a question: permission check, embedding, vector search, prompt building and a cited answer.
Document Ingestion for Vector Search
How documents become searchable passages for an AI assistant: extraction, cleaning, chunking, embedding and indexing, with changed files re-processed automatically.
MLOps Model Training Pipeline
Where each part of an MLOps setup runs: feature store, training jobs on GPU nodes, experiment tracking, model registry and automated deployment to serving.
ML Model Lifecycle
The states a machine learning model moves through, from experiment to production to retirement, including rollback when live performance drops.
LLM Gateway with Cost and Safety Controls
One gateway that every app in a company uses to reach language models: it applies budgets, rate limits, content filters and caching, and records usage per team.