# Two Approaches to Helping AI Agents Use Your API (And Why You Need Both)

DevFeed: [Two Approaches to Helping AI Agents Use Your API (And Why You Need Both)](<https://devfeed.tech/articles/two-approaches-to-helping-ai-agents-use-your-api-and-why-you-need-both-46739.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/skill-md-meets-repl/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-01-28T08:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [API](<https://devfeed.tech/topics/api.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Python](<https://devfeed.tech/topics/python.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [python](<https://devfeed.tech/tags/python.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

## AI overview

The article explains two complementary ways to help AI coding agents use APIs more reliably: SKILL.md files provide product-specific guidance about known pitfalls, while a Python REPL-first MCP approach lets agents discover user-specific resources and schemas directly.

## Source excerpt

AI coding agents fail in predictable ways when working with APIs. Two recent approaches from Mintlify and Armin Ronacher attack different failure modes. Understanding both reveals something useful about how agents should interact with developer tools. Two Failure Modes When an agent writes code against your API, it can fail because: It doesn't know what it doesn't know. The agent uses a deprecated method, misconfigures a parameter, or violates a constraint that isn't obvious from type signatures. This is the "known unknowns" problem: things the API maintainer knows but the agent doesn't.