CURRENT | Market Pulse

The Signal

Why Agent Platforms Still Deploy Humans

By Nora Kaplan— February 11, 2026

Feature image for article: Why Agent Platforms Still Deploy Humans

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.

Agent platforms deploy humans alongside their technology because operational knowledge exists in production environments, not yet consolidated into self-service infrastructure. The FDEs solve deployment problems, accumulating patterns that emerge only at production scale across heterogeneous environments. Whether that knowledge can ever fully consolidate into platform features remains uncertain. The economics only work if the discovery process eventually completes.

The Signal

Why Agent Platforms Still Deploy Humans

By Nora Kaplan— February 11, 2026

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.

Agent platforms deploy humans alongside their technology because operational knowledge exists in production environments, not yet consolidated into self-service infrastructure. The FDEs solve deployment problems, accumulating patterns that emerge only at production scale across heterogeneous environments. Whether that knowledge can ever fully consolidate into platform features remains uncertain. The economics only work if the discovery process eventually completes.

Where This Goes

Five Agent Trajectories Worth Watching Through Mid-2026

Several patterns from recent weeks deserve attention as they develop over the coming months.

OpenAI's Frontier platform treats agents like employees, complete with onboarding and identity management. Workforce systems may increasingly handle human and agent lifecycles together rather than separately.

The micropayment economy around agent transactions (89% priced under $0.10) could push traditional SaaS pricing toward granular consumption models. Visa's Trusted Agent Protocol, already enabling hundreds of controlled purchases, suggests commerce infrastructure being rebuilt to authenticate machines at machine speed.

Demand for AI Agent Architects has surged 300-500%. Specialization appears to be emerging between building individual agents and orchestrating systems at scale.

VoidLink malware, 88,000 lines written by AI in six days, raises questions about security models when threats develop at non-human speeds.

Where This Goes

Five Agent Trajectories Worth Watching Through Mid-2026

Several patterns from recent weeks deserve attention as they develop over the coming months.

OpenAI's Frontier platform treats agents like employees, complete with onboarding and identity management. Workforce systems may increasingly handle human and agent lifecycles together rather than separately.

The micropayment economy around agent transactions (89% priced under $0.10) could push traditional SaaS pricing toward granular consumption models. Visa's Trusted Agent Protocol, already enabling hundreds of controlled purchases, suggests commerce infrastructure being rebuilt to authenticate machines at machine speed.

Demand for AI Agent Architects has surged 300-500%. Specialization appears to be emerging between building individual agents and orchestrating systems at scale.

VoidLink malware, 88,000 lines written by AI in six days, raises questions about security models when threats develop at non-human speeds.

IN SUMMARY

Workforce convergence:

McKinsey operates 20,000 AI agents alongside 40,000 humans while BNY Mellon deploys similar scale, with HR and IT systems beginning to merge around agent lifecycle management.

Payment infrastructure:

x402 processed over 20 million agent transactions in January, with average prices dropping from $0.81 to $0.29 as micropayment rails optimize for machine commerce.

Commerce authentication:

Over 100 partners building within Visa's ecosystem to distinguish legitimate shopping agents from malicious bots, signaling checkout flows being redesigned for autonomous purchasing.

Threat velocity:

Security researchers confirmed sophisticated Linux malware created entirely by AI in six days versus traditional 30-week timeline, while consumer fraud losses jumped 25% despite flat volumes.

Skills premium:

AI Agent Architects commanding significantly higher salaries than traditional software engineers as enterprises discover the gap between framework capabilities and business logic translation at scale.

From the Labs

Graph-Based Agent Memory: From Logs to Topology

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

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

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

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.

From the Labs

Graph-Based Agent Memory: From Logs to Topology

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.

From the Labs

Memory in the Age of AI Agents: Unified Taxonomy

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.

From the Labs

Agent Workflow Memory: Learning Reusable Task Patterns

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.

From the Labs

A-MEM: Self-Organizing Memory Using Zettelkasten Principles

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.

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.

Durable Execution

Fault Tolerance as Built-In Primitive

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.

Workload Isolation

Kernel-Level Sandboxing for Agent Code

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.

Database Infrastructure

Zero-Copy Forks for Isolated Testing

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.

Observability Standards

OpenTelemetry Conventions for Agent Traces

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.

Telemetry Graphs

Semantic Context for Agent Diagnostics

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.

Cost Infrastructure

Real-Time Tracking for Agent Economics

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

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

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

Gravitee: 88% Hit Agent Security Incidents in Production

Cloud Security Alliance: 78% Still Use API Keys for Agents

Anthropic Engineering: How We Actually Evaluate Our Agents

What We're Reading

LangChain Survey: Everyone Watches Agents, Half Never Test Them1,300 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 ScoringMulti-step agents break prompt-response testing. Practical framework for why tracing becomes foundational, not optional, for production evaluation.

Quick links

Microsoft: 29% of Fortune 500 Agent Usage Is Shadow AI

Gravitee: 88% Hit Agent Security Incidents in Production

Cloud Security Alliance: 78% Still Use API Keys for Agents

Anthropic Engineering: How We Actually Evaluate Our Agents