Salesforce

WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar

Jul 14, 2026 · 20:54

Prukalpa Sankar, founder of Atlan, argues that the missing infrastructure for production AI agents is a 'context layer' that encodes business knowledge, expertise, and norms into machine-usable form. She describes how her team built 300 skills and 40 agents but hit problems like context sprawl, dependency management, and skill quality. Sankar proposes a context layer with versioning, lifecycle management, and compounding learning loops from agent traces, enabling teams to share and maintain business context like code. She concludes that context is both king and intellectual property, differentiating companies when models and intelligence are commoditized.

Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked

May 3, 2026 · 1:41:25

Peter Werry of Unblocked argues that context engines—systems that supply AI agents with only the relevant organizational context—are critical to avoid agent doom loops and wasted tokens. He debunks three myths: naive RAG, connecting MCP servers, and bigger context windows do not solve the context problem. Werry describes building a social engineering graph to identify experts and distill team best practices, and shares hard lessons including hiding conflicts and caching answers. In a benchmark task, Unblocked's context engine reduced a 2.5-hour, 21-million-token task to 25 minutes and 10 million tokens. The talk offers a practitioner's guide to building context engines with conflict resolution, personalization, and access control.

A2A & MCP Workshop: Automating Business Processes with LLMs — Damien Murphy, Bench

Jul 26, 2025 · 1:23:14

Damien Murphy presents A2A and MCP protocols for building multi-agent systems that automate business processes from webhooks, using a host agent that delegates tasks to sub-agents (Slack, GitHub, Bench) via A2A, with each sub-agent using MCP tools from Zapier or internal APIs. He demonstrates processing a meeting transcript to create a GitHub issue, send a Slack message, and research attendees, emphasizing that A2A handles remote agent discovery and opaqueness while MCP provides standardized third-party tool access. Murphy highlights benefits like context isolation—sub-agents absorb large tool outputs and keep the host's context small—and parallel processing, but notes limitations: A2A's early stage, MCP's silent failures (e.g., Zapier Slack missing channels), the non-determinism of LLM orchestration, and the challenge of prompt caching costs. He argues that A2A is best for third-party agents where complexity is hidden, while MCP is useful for extensible tool integration, but if you control the tools or agents, direct function calls are simpler and more reliable.

The Hidden Costs of Building Your Own RAG Stack — Ofer Vectara

Feb 22, 2025 · 15:14

Ofer from Vectara argues that building your own RAG stack comes with seven hidden costs: irrelevant responses and hallucinations, high latency, scaling and cost issues, security and compliance challenges, vendor chaos from multiple components, unsustainable expertise requirements, and limited non-English language support. He details how each pitfall compounds at enterprise scale, citing the need for hybrid search, reranking, and continuous evaluation to maintain quality. Vectara offers a turnkey RAG-as-a-service platform that handles parsing, chunking, embedding, vector search, retrieval, and hallucination detection. Ofer highlights Vectara’s open-source HHEM model for hallucination evaluation, downloaded over 3 million times, and a leaderboard showing some LLMs hallucinate at rates above 10%. The platform supports deployment in SaaS, VPC, or on-premises, with built-in access control and explainability.

Cohere: Building enterprise LLM agents that work (Shaan Desai)

Feb 22, 2025 · 18:29

Shaan Desai, a machine learning engineer at Cohere, presents key strategies for building enterprise LLM agents that are scalable, safe, and seamless. He recommends using native or LangGraph frameworks for high observability in large-scale agents, while CrewAI or AutoGen suit quick proofs of concept. Core insights include starting with a single LLM and a handful of tools, simplifying tool specifications with clear descriptions and sharp examples, and caching chat history to prevent hallucinations beyond 20 turns. For multi-agent setups, the router needs clear routing instructions for edge cases, and sub-agents should be constrained to independent tasks. Safety is paramount, with human-in-the-loop triggered before or after tool calls based on codified rules. Evaluation uses a golden set of ground truth queries, expected tool calls, and outputs. Failure mitigation ranges from prompt engineering for low-severity issues to targeted annotation datasets for 10–20% failure rates and synthetic data fine-tuning for high failure rates. Cohere packages these learnings into NORTH, a single container deployment with RAG, vector DBs, and connectivity to Gmail, Outlook, Drive, and Slack,…