LangTalks AI Engineering Conference 2026

As we run more agents in parallel, it becomes clear: we are the bottleneck. Luckily, the skills we need for effective multi-agent orchestration aren’t entirely new, they’ve just been hiding in unexpected places.Through AgentCraft, the game-inspired agent orchestrator, I’ll explore how we can raise the ceiling of human-agent collaboration without burning out in the process.

Harness core concepts and practices — what we've learned building OpenClaw and Hermes. Why we rolled our own, what skill-driven development actually means day to day, and how autonomy starts to compound once the scaffolding is right. PepperClaw (Lee) — an AI chief of staff. Workflows as markdown files, and a fail-driven loop where the agent rewrites its own rules from your edits. Walking through the GTM engineering use case end-to-end: morning prep, meeting analysis, follow-up drafts. Hyped (Gal) — a Telegram-native harness for managing virtual developers from your phone. Voice in, voice out, video as proof-of-work, visual planning, live calls with your agents. The bet: managing agents should look more like managing a team than running a script.

Building the #1 deep research agent was not about adding more complexity, but about doing less with focus and discipline. In this talk, we share our journey from early experiments to production, the core challenges we faced, how we approached token efficiency and evaluations, and what the next generation of research agents will look like.

Silent failures are the hardest bugs in AI engineering: the system "works," but it's quietly suboptimal: less accurate, less reliable, or more expensive than it should be. What are the most common pitfalls that lead to this hidden underperformance, and how can we design systems to detect it and prevent it early?

Creating agents that live and work inside a discord channel and talk to each other. We can add a new agent and show how they work together and can be modified.

Building a cool AI demo is easy; maintaining hundreds of unique deployments for healthcare clients without ballooning your engineering head-count is the real challenge. At Hyro, we spent five years evolving from a code-forward NLP approach to a sophisticated, LLM-driven multi-agent system handling over 700,000 conversations weekly. We share the honest growing pains moving to a unified, scalable platform where Solutions Engineers can deploy complex, reliable agents independently.

Most teams reach for better prompts when agents break. AutonomyAI reaches for the harness. This talk introduces harness engineering as the discipline of making mistakes structurally impossible, then walks through how AutonomyAI runs two harnesses in parallel: an internal R&D lab where patterns are tested against real evals, and a product harness that personalizes per customer codebase. The two are connected by a flywheel: every customer trace sharpens the lab, every lab experiment ships to every customer. When models plateau, harnesses compound.

Autonomous BizDev AI employee for SLED AI. Finds, validates and acts on the US government market.

AI video can look impressive - but still feel off. In this talk, we’ll break down how to use Seedance 2.0 to create video that feels real, not just visually appealing. We’ll cover the workflows, shortcuts, and production techniques that turn quick generations into consistent, high-quality results. We’ll also touch on how combining tools like Higgsfield and Claude with strong prompting skills enables better control, faster iteration, and more reliable outputs. How do we move from generation to real production?

In the era of coding agents, scaling a codebase isn't just about writing more code faster — it's about building systems that agents and humans can navigate safely and predictably. Live coding demo covering: the Dev-X setup built for both developers and coding agents, Skills & Standards, and why SOLID principles and Design Patterns matter more than ever when agents are writing your code.

Cloud platforms generate massive security data: events, resources, connections. Manual investigation doesn't scale. We built fully autonomous AI agents that investigate from alert to verdict, operating 10x faster than humans through context management, adaptive replanning, and evaluation metrics.

Everyone says "use a Knowledge Graph for RAG," but nobody tells you how much it hurts when you actually try to build it. After thousands of hours trying to turn complex books and multi-modal content into an interactive learning experience, we share every mistake made with Neo4j and LLMs — why extracting knowledge from a 300-page book is harder than searching a billion-row database, how the graph evolved from "too simple to work" to "too complex to query," and real-world examples of where RAG failed and how GraphRAG saved (and occasionally broke) the experience.