# AI workflows improve through iteration, not instant automation

Markdown copy of https://realalpha.app/s/ai-workflows-improve-through-iteration-not-instant/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Angela McNeal](https://realalpha.app/builders/angela-mcneal/) · Angela McNeal is CEO and cofounder of Thread AI. · Built Lemma, Thread AI’s orchestration platform for governed AI workflows and agents in mission-critical enterprise operations.
- Host: [Theo Jaffee](https://realalpha.app/people/theo-jaffee/) · Co-founder & host, MTS · One of the first members of a16z's new media team; earlier hosted the Emergent Ventures-backed Theo Jaffee Podcast.
- Host: [Sophia Dew](https://realalpha.app/people/sophia-dew/) · Host, MTS
- Show: MTS
- Episode: [Why Full AI Automation Fails in Production | Angela McNea](https://realalpha.app/v/DwrYJCnoHZs/), Nov 8, 2026
- Moment: 25:27 to 27:50 of the episode (2 min), playing on https://realalpha.app/s/ai-workflows-improve-through-iteration-not-instant/; the episode from there: https://realalpha.app/v/DwrYJCnoHZs/?t=1527

## Quote

> “AI workflows are **always iterative** so you're not going to have the perfect automated system”
> — [Angela McNeal](https://realalpha.app/builders/angela-mcneal/) at [27:13](https://realalpha.app/v/DwrYJCnoHZs/?t=1633) · MTS

## Takeaways

1. Broad decision-making is harder to automate than constrained tasks.
2. Start with a working process rather than waiting for a perfect agent.
3. Capture human-AI interactions so the system can improve.

## About this segment

Angela McNeal argues that broad decision-making remains difficult to automate, while constrained tasks work better. Teams should start with human input, capture the exchange, and improve the system over time.

From “Why Full AI Automation Fails in Production | Angela McNea”, Nov 8, 2026. [Watch the full episode](https://realalpha.app/v/DwrYJCnoHZs/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[25:31](https://realalpha.app/v/DwrYJCnoHZs/?t=1531) right the skill that you have yeah yeah um and i guess last question uh before we wrap um what have you found has been like maybe notoriously difficult to automate um in building like thread AI but even just like insights that you may have seen into industries yeah um I think they uh there are a lot of interesting ways um yeah I guess I think decision so decision making yeah yeah yeah um where um I'm not in the again and this is maybe also a hot take, I'm not in the AGI camp.

[26:11](https://realalpha.app/v/DwrYJCnoHZs/?t=1571) Oh, interesting. Yeah, yeah, yeah. You're on the AGI show. I believe in, like, intelligent systems and that, you know, we're building intelligent systems and using intelligent systems. You know, we can talk definitions all day, but I think a lot of the decision-making that I've seen attempted to be automated across the stack, across the process, be kind of unsuccessful except when the feature space is so constrained where you have a finite number of paths a finite number of opportunities whether it's like cool route to this person or hey do this thing or maybe we try this and be successful but when you like open up the aperture I've seen things struggle still but I think part of that is and I also used to say this also too past life of the death to innovation is also too this inability to get started

[27:17](https://realalpha.app/v/DwrYJCnoHZs/?t=1637) and AI workflows are always iterative so you're not going to have the perfect automated system the perfect agent out of the get-go from the beginning you need to start and put in the building blocks and make sure that you're capturing the right information You're capturing that human AI exchange and then you're building this data asset that then your system can learn from and then get more intelligent and evolve over time.

[27:38](https://realalpha.app/v/DwrYJCnoHZs/?t=1658) And so I think it's the expectation often that like, cool, I can automate every decision, everything from the beginning. Yeah. But in reality, you know, it's going to take a little bit. Yeah. Yeah.