Teacher since November 2025
Ingrid Solberg
I teach people to make AI agents safe, observable and testable before they are trusted with real work
9
tutors built
4.5Sample
average from 17 reviews
290Sample
lessons taught by their tutors
About Ingrid
My background is in quality assurance and security testing, and I came to agents through the question every tester asks: how do we know this thing works, and what happens when it does not? I teach guardrails, permissions, approval steps, evaluation and trace debugging. My lessons are concrete. We look at a failure, name it, and design the check that would have caught it. I try hard not to scare people or to sell certainty. Agents can be useful and they can be made much safer, but no setup removes every risk, and I say so plainly. I enjoy working with both engineers and the managers who have to sign off on what agents may do.
Knows about
Tutors by Ingrid
9 tutors
Reading and Debugging Agent Traces
Read an agent's step by step record and find where and why a run went wrong64 lessonsSampleIngrid Solberg$8Agent Failure Modes and How to Spot ThemAgent Failure Modes and How to Spot Them
Learn the common ways AI agents go wrong so you can recognise them early and respond calmly61 lessonsSampleIngrid Solberg$4Guardrails and Permissions for AI AgentsGuardrails and Permissions for AI Agents
Decide what your agent may read, write and spend, and enforce those limits in code rather than prompts56 lessonsSampleIngrid Solberg$8Letting an AI Assistant Act for You: Safety BasicsLetting an AI Assistant Act for You: Safety Basics
Use assistants that can browse, send or book on your behalf without handing over more than you meant to48 lessonsSampleIngrid SolbergFreePrompt Injection and Agent SecurityPrompt Injection and Agent Security
Understand how untrusted text hijacks agents and design systems that limit the damage when it does45 lessonsSampleIngrid Solberg$13Human Approval Steps in Agent WorkflowsHuman Approval Steps in Agent Workflows
Place human checkpoints where they actually catch mistakes, without turning reviewers into rubber stamps16 lessonsSampleIngrid Solberg$4Sandboxing Agents That Run CodeSandboxing Agents That Run Code
Isolate code executing agents so a bad command cannot reach your files, network or secretsIngrid Solberg$13Evaluating Agents: Tasks, Trajectories and ScoresEvaluating Agents: Tasks, Trajectories and Scores
Build an evaluation suite that tells you whether an agent change made things better or worseIngrid Solberg$12Monitoring Agents in ProductionMonitoring Agents in Production
Know what your live agent is doing, catch quality drops early and respond to incidents with a planIngrid Solberg$9Recent reviews
What students said about Ingrid's tutors.
- Filip S.Sample
Solid, but I already had decent tracing, so the first two lessons were review for me. The patterns lesson was the useful part.
- Tariq Z.Sample
Short and practical. My checklist is on my fridge. I wanted a little more about privacy policies, but it pointed me in the right direction.
- Clara J.Sample
The risk tier exercise was simple and effective. I would have liked a sample permission plan to compare mine against, but the structure was clear.
- Margaret H.Sample
I am seventy and nervous about this stuff. The house key comparison made sense, and I now know which settings to look for. Kind and clear.
- Vikram P.Sample
Calm, no scare tactics, very concrete. Exactly the tone I needed before presenting to our security lead.
- George K.Sample
Good practice traces. I would have liked one with subagents in the mix, but the method transfers.