Presentation Directory
Every session from LangChain Interrupt 2026, in running order. Talks we recorded link to a full page (synthesis + complete transcript); sessions we did not capture are summarized from the published agenda.
Quick Digest Table
| Ref # | Track | Presentation | Take Aways |
|---|---|---|---|
| 1.1 | Keynotes | Day 1 Keynote: The Deep Agents Era | Deep agents = batteries-included agent harness Deep Agent 0.6: open models + Code Interpreter + streaming SmithDB (Rust) makes traces 6-15x faster LangSmith Engine: ambient issue-fixing agent |
| 1.2 | MC Opening Remarks & Housekeeping | Last year: do agents work? This year: yes Logistics + sponsors Cisco CX is presenting sponsor | |
| 1.3 | Case Studies | Building Frontier CX Agents | Chatbot to delegating teammate Dynamic plan-based supervisor graphs 95% accuracy wasn't enough; adoption plateaued Routing is your first decision |
| 1.4 | Scaling GTM Agents (not recorded) | Not recorded — summary from the public agenda. | |
| 1.5 | The Production System for Agents | 6 months/6 engineers became 4 days/1 engineer 50,000+ agents in production Gateball: hours of manual search to ~10s LangChain mapped to TPS principles | |
| 1.6 | Engineering & Evaluation | How Lyft Builds Evals That Actually Matter in Production | Treat AI evals like traditional ML Offline eval = quality gate; don't test on users Built a tau-bench-style simulator with mocked MCP Frame LLM-as-judge around agent tasks (talk cuts off) |
| 1.7 | Make Legal Write Your Evals | Evals are the alignment surface that removes the language barrier between engineers and legal Break vague risk into a taxonomy of domains, categories, and concrete risks Legal writes structured risk definitions that bootstrap both datasets and LLM-as-judge evaluators Aggregate pass rates at every altitude so engineers, compliance, and executives each get the view they need A feedback flywheel turns one annotation into four improvements; compliance signals arrive in hours, not at the release date | |
| 1.8 | Product & Launches | Introducing Managed Deep Agents | An agent = model + harness; the harness delivers the right context at the right time Deep Agents harness has four capabilities: execution environment, context management, delegation, steering Context management uses summarization, offloading, memory, prompt caching, and progressively-disclosed skills Provider-agnostic and customizable via middleware hooks around the core agent loop Managed Deep Agents (private beta) adds production runtime, durable checkpointing, Context Hub, and LangChain sandboxes |
| 1.9 | How We Built It: LangSmith Engine | LangSmith Engine is an agent that finds, clusters, and fixes agent issues from production traces It proposes prompt/code fixes as one-click GitHub PRs and builds online evaluators plus ground-truth datasets Hardest part is identifying meaningful issues, not generating fixes—Engine was at first 'too good at finding problems' Traces are the window to the agent's soul; Engine ingests condensed traces and runs on deep agents + LangSmith sandboxes Per-team priorities are learned via an 'agent coverture' memory file, and Engine even improves itself by feeding its own traces back in | |
| 1.10 | Case Studies | Building Deep Agent Sidekick (not recorded) | Not recorded — summary from the public agenda. |
| 1.11 | Intelligent Agents in Aviation (not recorded) | Not recorded — summary from the public agenda. | |
| 1.12 | Fireside Chats | Agents in the Enterprise | Coding agents win because output is verifiable, users are technical, and permissions are open—knowledge work is the opposite Expect years of deployment and change management; doers will be wrong on the take-off due to slow diffusion Decade-old single-file-system/single-governance bets at Box now pay off for agents Build a world-class product AND world-class headless APIs; volume will skew headless (Salesforce went headless) Build on a coding-agent harness for all knowledge work, and expect cost to drive enterprises toward multi-model setups |
| 1.13 | Case Studies | Lessons Learned Building Rippling AI (not recorded) | Not recorded — summary from the public agenda. |
| 2.1 | Keynotes | Day 2 Keynote (Closing) & Introduction of Carlos Pereira | Free open-source model added (powered by Fireworks) Closing keynote hands off to Carlos Pereira of Cisco CX |
| 2.2 | Case Studies | Observing and Testing CX Agents | Every thumbs-down is a signal, not noise Continuous feedback loop: traces to AI-diagnosed PRs to permanent regression tests Evals are infrastructure, not a side project MCP as integration layer lets you swap backends without touching agents Keep humans for decisions only |
| 2.3 | The Etsy Gifting Assistant: From Prototype to Production (not recorded) | Not recorded — summary from the public agenda. | |
| 2.4 | 60% Faster Time-to-Interview: Transforming Hiring with AI Agents | 60% faster time-to-interview with hiring agents on LangChain/LangGraph On-stage speakers introduce themselves as 'Grace' and 'Chok' (agenda lists Shang Liu and Tracy He) Evolved from chains to a central LLM planner running plan-act-replan Harness engineering and customization are the durable differentiation | |
| 2.5 | Product & Launches | Run Untrusted Agent Code with LangSmith Sandboxes | Agents are writing real code today across coding, data analysis, security, and browser control Untrusted code execution is risky: supply-chain, sandbox-escape, and prompt-injection incidents LangSmith Sandboxes: fast spin-up (~0.98s), egress proxy, durable pause/resume with no time limit, snapshot/fork One line to start, available on all plans, bring-your-own Docker images, full tracing |
| 2.6 | Fireside Chats | Future of AI Agents | Build with small, high-context generalist tasks given guardrails AI experiments often yield incremental efficiency, not transformation; redesign the whole workflow top-down Chase growth over cost savings: growth has almost no practical ceiling Preserve optionality with vendor-neutral tools and open-weight models Unstructured-data re-architecture is the next big enterprise challenge |
| 2.7 | Agents in the Enterprise | MongoDB = best DB for unstructured data, 'almost a coincidence' 11 Labs: 14M production agents after migrating to MongoDB ~70% of MongoDB's checked-in code last week came from coding agents Customer-facing agents at scale are the real prize — most enterprises aren't there yet | |
| 2.8 | Case Studies | Building AI for Healthcare | Abridge: 250 top US health systems, 100M+ conversations/year 'Trust is earned in drops but lost in buckets' LangGraph + LangSmith + APO judges cut releases from 1-2 months to days Reference-free + reference-based judges; you don't have to trade velocity for quality |
| 2.9 | Building Pat, the AI Pocket Analyst | Pat: hours of research in minutes, hundreds of investors daily 'The plan really is the analysis' — plan once, generate code in parallel Human-like search inspection lifted accuracy ~15% to 90% Treat agentic coding as a compiler problem; correctness enforced in architecture (95% identical output) | |
| 2.10 | Building Developer Support Agents | Coinbase dev-support: zero to one self-improving agent system Self-hosted LangSmith tracing + MCP docs server with RAG fallback LLM judge on accuracy and risk; intent-based workflow from traces Treat agent engineering as a discipline; build the glass box first; the team is the multiplier | |
| 2.11 | Closing | The Return of the Data Scientist | The return of the data scientist: experiment, measure, improve Most important takeaway: 'always look at your data' Skills to audit your evals for correctness (Recording captured only the open/close — middle not picked up) |