#049 BAML: The Programming Language That Turns LLMs into Predictable Functions

Nicolay here, I think by now we are done with marveling at the latest benchmark scores of the models. It doesn’t tell us much anymore that the latest generation outscores the previous by a few basis points. If you don’t know how the LLM performs on your task, you are just duct taping LLMs into your systems. If your LLM-powered app can’t survive a malformed emoji, you’re shipping liability, not software. Today, I sat down with **Vaibhav** (co-founder of Boundary) to dissect **BAML**—a DSL that treats every LLM call as a typed function. It’s like swapping duct-taped Python scripts for a purpose-built compiler. Vaibhav advocates for building first principle based primitives. One principle stood out: **LLMs are just functions; build like that from day 1.** Wrap them, test them, and let a human only where it counts. Once you adopt that frame, reliability patterns fall into place: fallback heuristics, model swaps, classifiers—same playbook we already use for flaky APIs. **💡 Core Concepts** - **Schema-Aligned Parsing (SAP)** Parse first, panic later. The model can handle Markdown, half-baked YAML, or rogue quotes—SAP puts it into your declared type or raises. No silent corruption. - **Symbol Tuning** Labels eat up tokens and often don’t help with your accuracy (in some cases they even hurt). Rename `PasswordReset` to `C7`, keep the description human-readable. - **Durable Execution** Durable execution refers to a computing paradigm where program execution state persists despite failures, interruptions, or crashes. It ensures that operations resume exactly where they left off, maintaining progress even when systems go down. - **Prompt Compression** Every extra token is latency, cost, and entropy. Axe filler words until the prompt reads like assembly. If output degrades, you cut too deep—back off one line. 📶 **Connect with Vaibhav:** - [LinkedIn](https://www.linkedin.com/in/vaigup/) - [X / Twitter](https://x.com/hellovai) - [BAML](https://github.com/boundaryml/baml) 📶 **Connect with Nicolay:** - [Newsletter](https://nicolaygerold.substack.com/subscribe) - [LinkedIn](https://www.linkedin.com/in/nicolay-gerold/) - [X / Twitter](https://x.com/nicolaygerold) - [Bluesky](https://bsky.app/profile/nicolaygerold.com) - [Website](https://www.nicolaygerold.com/) - [My Agency Aisbach](https://www.aisbach.com/) (for ai implementations / strategy) **⏱️ Important Moments** - **New DSL vs. Python Glue** [00:54] Why bolting yet another microservice onto your stack is cowardice; BAML compiles instead of copies. - **Three-Nines on Flaky Models** [04:27] Designing retries, fallbacks, and human overrides when GPT eats dirt 5 % of the time. - **Native Go SDK & OpenAPI Fatigue** [06:32] Killing thousand-line generated clients; typing `go get` instead. - **“LLM = Pure Function” Mental Model** [15:58] Replace mysticism with `f(input) → output`; unit-test like any other function. - **Tool-Calling as a Switch Statement** [18:19] Multi-tool orchestration boils down to `switch(action) {…}`—no cosmic “agent” needed. - **Sneak Peek—`durable` Keyword** [24:49] Crash-safe workflows without shoving state into S3 and praying. - **Symbol Tuning Demo** [31:35] Swapping verbose labels for `C0`,`C1` slashes token cost and bias in one shot. - **Inside SAP Coercion Logic** [47:31] Int arrays to ints, scalars to lists, bad casts raise—deterministic, no LLM in the loop. - **Frameworks vs. Primitives Rant** [52:32] Why BAML ships primitives and leaves the “batteries” to you—less magic, more control. **🛠️ Tools & Tech Mentioned** - [BAML DSL](https://docs.boundaryml.com/home) & [Playground](https://www.promptfiddle.com/) - [Temporal](https://temporal.io/) • [Prefect](https://www.prefect.io/) • [DBOS](https://www.dbos.dev/) - [outlines](https://github.com/dottxt-ai/outlines) • [Instructor](https://python.useinstructor.com/) • [LangChain](https://www.langchain.com/) **📚 Recommended Resources** - [BAML Docs](https://docs.boundaryml.com/home) - [Schema-Aligned Parsing (SAP)](https://www.boundaryml.com/blog/schema-aligned-parsing) **🔮 What's Next** Next week, we will continue going more into getting generative AI into production talking to Paul Iusztin. **💬 Join The Conversation** Follow How AI Is Built on [YouTube](https://www.youtube.com/@howaiisbuilt), [Bluesky](https://bsky.app/profile/howaiisbuilt.fm), or [Spotify](https://open.spotify.com/show/3hhSTyHSgKPVC4sw3H0NUc?_authfailed=1). If you have any suggestions for future guests, feel free to leave it in the comments or write me (Nicolay) directly on [LinkedIn](https://www.linkedin.com/in/nicolay-gerold/), [X](https://x.com/nicolaygerold), or [Bluesky](https://bsky.app/). Or at [email protected].