Define the boundary
Separate model proposals, trusted context, approvals, and tool execution.
Practical AI · EDITION 1.0.0
Design Reliable Agent Tool Contracts
Build an explicit boundary between an agent's proposed action and a tool's permitted effect, with strict inputs, bounded outputs, replay receipts, and failure tests.
By Sanjaay Gowda T S · For python developers adding tools to assistants and agents.
You need: Read Python functions and dictionaries; Run a local Python command; Understand JSON objects
Runtime and hardware details
Python 3.10 or later and a terminal. The supplied project runs locally and uses the Python standard library.
No model, API key, cloud account or network calls are used by the companion.
Read Python functions and dictionaries; Run a local Python command; Understand JSON objects.
Full setup and scope ↓$2.99USD · one-time purchase
Prepared with AI assistance. Independent human technical, editorial and assistive-technology reader review remains pending. Automated checks and agent review are not certification.
PDF + EPUB + companion project. Any applicable tax is shown at checkout. Single-reader ebook terms; companion code is MIT licensed.
TRY THE FREE SAMPLE
See how the guide teaches.
Read 7 sample pages to explore the introduction, first chapter and teaching approach before you choose the complete edition.
Read free sample PDF · No checkout required
WHAT YOU WILL LEARN
Understand each part.
Inspect every boundary.
Make retries explicit
Use payload-bound receipts and document ambiguous outcomes.
Test the contract
Reject malformed and unauthorized actions before mutation.
INSIDE THE BOOK
9 focused chapters.
- Begin with effects and invariants
- Write a contract the caller can follow
- Validate before doing work
- Bind authority to the exact action
- Design results for the next decision
- Make retries and receipts explicit
- Budget time and partial failure
- Test adversarial contract cases
- Version and operate the boundary
Your download includes
- 22-page tagged PDF with linked contents
- Reflowable EPUB for ebook readers
- Local Python project, fictional input, recorded expected JSON output and 11 companion tests
- 3 explanatory diagrams
- 9 chapters with exercises and worked answers
Before you begin
Python 3.10 or later and a terminal. The supplied project runs locally and uses the Python standard library.
No model, API key, cloud account or network calls are used by the companion.
Learning prerequisites: Read Python functions and dictionaries; Run a local Python command; Understand JSON objects.
Prepared with AI assistance. Independent human technical, editorial and assistive-technology reader review is pending.
The included examples are synthetic teaching material. Model access, software subscriptions, hosting, ongoing updates and consulting are not included.
CLEAR EXPECTATIONS
Before you buy.
What will I build?
Build an explicit boundary between an agent's proposed action and a tool's permitted effect, with strict inputs, bounded outputs, replay receipts, and failure tests. The local companion uses fictional teaching fixtures. Project limits: In-memory, single-process demonstration; no durable transaction or concurrent reservation protection. Approvals are trusted fictional fixtures, not authentication or a single-use approval service. No complete JSON Schema validator, model integration, network call or production timeout enforcement.
What was tested?
The 11 companion tests passed on the packaged project. The supplied fictional fixture produced its recorded expected JSON output. EPUBCheck reported no errors or warnings; DAISY Ace and PDF/UA automated checks passed. These local teaching checks are not production accuracy claims or certification. Independent human technical, editorial and assistive-technology reader review remains pending.
How do I get the files?
Complete the secure Lemon Squeezy checkout to access the PDF, EPUB and companion ZIP. Keep your receipt and download access private. This is a one-time purchase of edition 1.0.0; ongoing updates and consulting are not included.
Can I share the book or the companion code?
The full ebook is licensed to one reader. The labelled free sample may be shared unchanged. The companion project is MIT licensed and may be adapted or shared with its licence notice. See the exact ebook terms.
Validate actions, bind approvals, and make retries understandable
One book. A complete learning project. Evidence you can inspect.
AI-assisted · Independent human review pending
$2.99USDBuy ebook