Notifications
Clear all
Topic starter
07/06/2026 8:25 pm
TL;DR: Tiger Data says customers are seeing up to 70% of code generated by agents, while the company’s own Eon Slack bot reached 60% daily adoption in three weeks, underscoring how quickly agents are moving from novelty to core interface, according to WorkOS. The governance shift is that agent-facing systems now need identity, access, and observability models built for machine-paced API calls, not human UI sessions.
NHIMG editorial — based on content published by WorkOS: Tiger Data sees agents as the new developer interface
By the numbers:
- Customers are reporting 70% of their code comes from agents.
- 60% daily adoption within three weeks., ached 60% daily adoption within three weeks.
Questions worth separating out
Q: How should security teams govern AI agents that call APIs instead of using a UI?
A: Security teams should govern AI agents by treating each callable action as a scoped entitlement, not as a general application login.
Q: Why do AI agents create a different access problem from human developers?
A: AI agents create a different access problem because they can parallelise work, retrieve context on demand, and initiate actions without the pauses that human workflows naturally create.
Q: What breaks when an agent-facing tool set is too broad?
A: When an agent-facing tool set is too broad, the agent can combine capabilities in ways the governance model did not anticipate, which increases the blast radius of a single identity.
Practitioner guidance
- Map agent-facing affordances to explicit permissions Inventory every MCP tool, API call, and context source an agent can invoke, then treat each one as a distinct permission boundary with an owner and purpose.
- Test controls under agent-level concurrency Run load and abuse scenarios where a single identity initiates multiple parallel sandboxes, retrievals, and API actions so you can see where monitoring, throttling, or approval gates break down.
- Separate retrieval access from general application access Classify search indices, transcripts, Salesforce data, and other context sources as privileged inputs and restrict them by task scope rather than broad user convenience.
What's in the full article
WorkOS's full interview covers the product and engineering detail this post intentionally leaves for the source:
- Ajay Kulkarni’s direct explanation of why MCP design matters for agent-facing systems
- The internal Eon bot example showing how Tiger Data built agent workflows into daily operations
- More detail on why agents change database speed, sandboxing, and retrieval requirements
- The broader AWS re:Invent discussion that shaped the interview context
👉 Read WorkOS's interview with Tiger Data on AI agents as the new developer interface →
AI agents as the new developer interface: what changes for IAM teams?
Explore further
07/06/2026 10:18 pm
AI agents are pushing NHI governance from static entitlement thinking toward runtime capability control. Tiger Data’s description of agents that call APIs, chain tools, and work in parallel shows why human-session assumptions are no longer enough. The governance problem is no longer simply who has access, but what an identity can do once it starts composing actions across systems. Practitioners should treat agent toolsets as living permission surfaces, not fixed application menus.
A few things that frame the scale:
- When AWS credentials are exposed publicly, attackers attempt access within an average of 17 minutes, and as quickly as 9 minutes in some cases, according to LLMjacking: How Attackers Hijack AI Using Compromised NHIs.
- AI systems learning and reproducing sensitive information patterns from codebases concerns 43% of security professionals, according to The State of Secrets in AppSec.
A question worth separating out:
Q: How do IAM teams measure whether AI agent access is under control?
A: IAM teams should measure whether they can describe every agent action path, every context source, and every parallel execution pattern in audit terms. If reviewers cannot reconstruct what the agent could do and how much it could do at once, the programme is not yet governing the agent, only observing it. Auditability should include tool calls, retrievals, and downstream writes.
👉 Read our full editorial: AI agents are becoming the new developer interface for data tools
