--- title: "Market Pulse" canonical: "https://current.tinyfish.ai/issue/16/market-pulse" publication: "TinyFish" publisher: "TinyFish" language: "en-US" guide: "https://current.tinyfish.ai/llms.txt" permalink: "https://current.tinyfish.ai/issue/16/market-pulse" issue: 16 section: "market-pulse" description: "Reading the agent ecosystem through a practitioner's lens" authors: ["Nora Kaplan"] published: 2026-02-16 updated: 2026-07-16 articles: 18 --- # TinyFish > CURRENT is a journal about AI agents in production, for the engineering and product leaders who have to make them work. Drawing on experience building enterprise web agents, it explains why the demo succeeded and the deployment didn't, and what that means for choosing vendors, briefing the board, and avoiding mistakes others have already made. [Read on the website]() ## Issue 16 — Market Pulse Reading the agent ecosystem through a practitioner's lens ### The Week's Architecture Signal - [Why Agent Platforms Still Deploy Humans]() — By [Nora Kaplan]() · Published 2026-02-11 · Format: The Signal Salesforce is hiring Forward Deployed Engineers at a pace that saw job postings surge 800% in nine months. OpenAI's Frontier platform launched with FDEs who embed with enterprise teams through deployment. These are technical experts who stay through production, working alongside teams to get agents operational. ### Where This Goes - [Five Agent Trajectories Worth Watching Through Mid-2026]() — Published 2026-02-11 Several patterns from recent weeks deserve attention as they develop over the coming months. ### From the Labs - **Graph-Based Agent Memory: From Logs to Topology** — [Source]() — Published 2026-02-11 Survey analyzing how graph structures transform agent memory from passive logs into topological models that preserve relationships. Covers extraction, storage, retrieval, and evolution techniques with open-source libraries and benchmarks builders can actually use. Why graphs? They naturally model the hierarchical structure and causal dependencies web agents need for reliable multi-step workflows. What changes in practice? Relationships become first-class citizens in memory architecture, enabling complex reasoning that holds together over time. - **Memory in the Age of AI Agents: Unified Taxonomy** — [Source]() — Published 2026-02-11 Forty-seven authors consolidate fragmented agent memory research into unified taxonomy covering forms, functions, and dynamics. Distinguishes agent memory from LLM memorization across when learning happens, where it lives, and how it's governed. How much traction? Featured as Huggingface Daily Paper #1, GitHub repository hit 1,000 stars within six weeks of publication. Why read a taxonomy? Prevents architectural decisions that need rebuilding as the field matures and patterns become clearer. - **Agent Workflow Memory: Learning Reusable Task Patterns** — [Source]() — Published 2026-02-11 Enables agents to induce commonly reused workflows from past experiences and apply them to new situations. Tested on Mind2Web and WebArena benchmarks covering 1000+ tasks from 200+ domains, with significant improvements in success rates. What's the production angle? Agents become more reliable over time rather than starting from scratch with each new task. Where's the insight? Path to reliability comes from better memory of what worked before, not just better models. - **A-MEM: Self-Organizing Memory Using Zettelkasten Principles** — [Source]() — Published 2026-02-11 Memories actively generate their own contextual descriptions, form meaningful connections, and evolve structure over time. Inspired by proven human knowledge management system, exhibits agency at fundamental level through autonomous evolution of memory structure. What's different here? Memory becomes active, self-organizing component that adapts to deployment patterns rather than passive storage. How does this help? Memory adapts to specific patterns of each deployment rather than requiring manual tuning for production. ### Quiet Tech That Compounds Production agent systems depend on infrastructure that rarely makes headlines. Durable execution engines that survive crashes. Kernel-level sandboxing that isolates untrusted code. Database forks that spin up in seconds. Observability standards that work across frameworks. These capabilities matter because they solve the problems that keep agents in prototype purgatory. How do you make workflows survive server reboots? How do you track costs when agents run continuously? How do you test against production data without duplicating infrastructure? Six developments worth attention. Infrastructure improvements and operational tooling that serious builders care about because they make production systems actually work. - **Fault Tolerance as Built-In Primitive** — [Source]() — Published 2026-02-11 Tag: Durable Execution Temporal and Restate externalize agent state into systems designed for recovery. Processes crash mid-workflow and resume exactly where they stopped. No reimplemented retries, no lost progress. Reliability becomes infrastructure, not hand-coded logic that breaks under load. - **Kernel-Level Sandboxing for Agent Code** — [Source]() — Published 2026-02-11 Tag: Workload Isolation Google's Agent Sandbox uses gVisor to isolate LLM-generated code at the kernel level. Sub-second latency for fully isolated workloads. Kubernetes gets a native primitive for running untrusted agent code safely in production environments. - **Zero-Copy Forks for Isolated Testing** — [Source]() — Published 2026-02-11 Tag: Database Infrastructure Agentic Postgres provisions database forks in seconds using copy-on-write storage. Agents spin up isolated environments with full production data without duplicating costs. Testing becomes lightweight infrastructure instead of expensive replication. - **OpenTelemetry Conventions for Agent Traces** — [Source]() — Published 2026-02-11 Tag: Observability Standards Standardized semantic conventions define how to trace tasks, actions, agents, and memory across frameworks. Microsoft and Cisco are collaborating on consistent telemetry. Works whether you're using OpenAI, Anthropic, or LangChain. Cross-platform observability without vendor lock-in. - **Semantic Context for Agent Diagnostics** — [Source]() — Published 2026-02-11 Tag: Telemetry Graphs Knowledge graphs connect services, teams, datasets, and alarms with meaningful relationships. When alerts fire, agents navigate the graph to pull relevant metrics, logs, and traces. Understanding context instead of brute-forcing through raw telemetry. - **Real-Time Tracking for Agent Economics** — [Source]() — Published 2026-02-11 Tag: Cost Infrastructure Inference costs plummet but usage explodes. Enterprises need infrastructure to track agent spending in real time. Paid and similar platforms address the gap between per-seat pricing and continuous inference economics. ### What We're Reading - **LangChain Survey: Everyone Watches Agents, Half Never Test Them** — [Source]() — Published 2026-02-11 1,300 practitioners admit the gap: 89% add observability, 52% skip systematic evaluation. Monitoring without validation is just expensive logging. - **Braintrust: Why Agent Evaluation Needs Infrastructure, Not Scoring** — [Source]() — Published 2026-02-11 Multi-step agents break prompt-response testing. Practical framework for why tracing becomes foundational, not optional, for production evaluation. - **Microsoft: 29% of Fortune 500 Agent Usage Is Shadow AI** — [Source]() — Published 2026-02-11 Deployment velocity outpaces governance infrastructure. The real number: organizations building agent capabilities faster than they can establish controls. - **Gravitee: 88% Hit Agent Security Incidents in Production** — [Source]() — Published 2026-02-11 Security failures moved from theoretical risk to baseline reality. Survey of 900+ executives shows incidents are infrastructure problems now. - **Cloud Security Alliance: 78% Still Use API Keys for Agents** — [Source]() — Published 2026-02-11 Only 22% treat agents as independent identities. Shared credentials and API keys reveal how far behind identity architecture lags deployment. - **Anthropic Engineering: How We Actually Evaluate Our Agents** — [Source]() — Published 2026-02-11 Rare practitioner view from builders shipping production systems. Dedicated eval teams plus domain experts owning task definitions. The model that works. ## Other sections in Issue 16 - [Daily Brief]() - [Foundations]() - [Practitioner's Corner]() - [Echoes]() - [Vision]() ## More - [Publication guide]() - [Issue archive]()