Notifications
Clear all
Topic starter
18/08/2026 2:51 pm
TL;DR: Agentic software factories move AI coding agents inside the delivery pipeline, which changes throughput, review economics, and identity requirements, according to TruFoundry’s analysis. The core security issue is not the agent itself but the utilities layer around model supply, credential handling, quality control, telemetry, and spend metering, where existing IAM and control assumptions are easiest to overrun.
NHIMG editorial — based on content published by TruFoundry: The Agentic Software Factory, Explained: History, Architecture, and Enterprise Controls
By the numbers:
- In the first half of 2026, some organizations operating the agentic software factory model described productivity gains of 3 to 5 times.
- 60% to 90% time savings in the studied, 0% to 90% time savings in the studied cases.
Questions worth separating out
Q: How should security teams govern AI-generated code in production pipelines?
A: Security teams should treat AI-generated code as a controlled identity event, not just a development artifact.
Q: Why do agentic software factories increase identity risk?
A: They compress more decision-making into a shorter execution window, which expands the potential blast radius of every credential and tool invocation.
Q: What do teams get wrong about MCP gateways and agent governance?
A: They assume a gateway covers the whole factory.
Practitioner guidance
- Map every access path before scaling agents Inventory mediated paths, direct APIs, browser access, shell operations, CI jobs, and downstream system calls.
- Centralize credential custody for agent-facing tools Use managed credential injection or supported OAuth patterns instead of embedding secrets in agent definitions.
- Require approval gates for high-impact actions Separate low-risk retrieval from code changes, deployment steps, and data-altering actions.
What's in the full article
TruFoundry's full article covers the operational detail this post intentionally leaves for the source:
- The full utilities-layer checklist for model supply, credential handling, quality control, telemetry, and spend metering.
- Architecture notes on MCP gateway mediation, including where centralised controls stop and bypass paths begin.
- Examples of enterprise controls to evaluate before scaling agentic delivery, such as traceability and authorisation gates.
- The article's detailed comparisons between software factories, loop engineering, and platform engineering.
👉 Read TruFoundry’s analysis of the agentic software factory and enterprise controls →
Agentic software factories: what controls do IAM teams need now?
Explore further
18/08/2026 3:33 pm
The utilities layer, not the agent model, is the real governance boundary. Agentic software factories fail when teams focus on the worker and ignore the mediated infrastructure that hands out access, logs actions, and enforces limits. In identity terms, model routing, credential custody, and tool mediation are the equivalent of power, plumbing, and metering in a physical plant. Practitioners should govern the layer that grants and records authority, not the model that consumes it.
A few things that frame the scale:
- 98% of companies plan to deploy even more AI agents within the next 12 months, despite documented rogue behaviour in 80% of current deployments, according to AI Agents: The New Attack Surface report.
- Only 52% of companies can track and audit the data their AI agents access, which leaves 48% with a compliance and investigation blind spot.
A question worth separating out:
Q: What should organisations review before expanding agentic delivery?
A: Review model access, credential custody, intermediate quality checks, traceability, cost controls, and human authorization in proportion to what the system can access and change. If those controls are uneven, scale amplifies both defect rate and security impact instead of reducing them.
👉 Read our full editorial: Agentic software factories need stronger identity and utility controls
