Source URL: https://www.tomtunguz.com/agentic-workflows/
Source: Tomasz Tunguz
Title: Stuck in the Middle of AI Workflows
Feedly Summary: Whenever I hear about a new startup, I pull out my research playbook. First, I understand the pitch, then find backgrounds of the team, & tally the total raised.1
Over the weekend, I decided to migrate this workflow to use AI tools, & the process taught me something important about how we’re actually integrating AI into our work.
Tools are small programs that expand AI capabilities. ChatGPT might call a web search tool to read a blog post I’d like to summarized. Claude might call the terminal tool to change file permissions in my current directory. Gemini might call a tool to find the latest stock price of the most recent IPO I’ve been following.
I replaced each step in my workflow with an AI tool: a web search & summarization tool, LinkedIn research tool, & a capital fundraising history tool. I hadn’t changed the workflow itself—just swapped out the individual components within it.
This upgrade revealed something crucial: there are three distinct classes of programs emerging in enterprise software.
Deterministic workflows are my original startup research process—the same steps, in the same order, every time. These excel at mechanization, executing identical processes with small deviations or calculations at each step.
Deterministic workflows with AI components represent my current setup. I still follow the same research sequence, but now Gemini & ChatGPT handle the summarization. The AI makes individual steps smarter while I maintain control over the overall process.
Agentic workflows hand decision-making to the AI entirely. The system decides what to research, in what order, & which tools to call based on the input.
These excel at handling broad universes of potential inputs—like customer support where a user might ask “Why won’t my password reset?” or “Can I integrate your API with Salesforce?” or “My data export is corrupted”—questions that require completely different investigative paths.
Security incident response works similarly: when an alert fires, an agentic system might investigate network logs, check for similar patterns in historical data, or escalate to human analysts based on threat severity—decisions that can’t be predetermined because each incident presents unique characteristics.
I learned two things from this migration:
Programming with AI tools is remarkably simpler. AI categorizes companies far better than any rule-based system I could write.
I hadn’t built an agentic workflow—I was just upgrading my deterministic process with intelligent components. & that’s exactly what I wanted.
I don’t want an AI deciding how to diligence a company. I want it to diligence every AI software company the same way, every time. The consistency of my process combined with the intelligence of AI gives me the balance I need: repeatable methodology enhanced by superior pattern recognition.
Maybe I’ll evolve toward fully agentic startup diligence someday, especially as the models improve.
But for now, this hybrid approach delivers the reliability of deterministic processes with the power of AI—& that’s the sweet spot for most enterprise applications today.
AI Summary and Description: Yes
Summary: The text discusses the integration of AI tools into established workflows, emphasizing the transition from deterministic processes to a hybrid approach incorporating AI for enhanced efficiency. It particularly highlights the different classes of workflows: deterministic, AI-enhanced deterministic, and agentic, providing insights for security, compliance, and operational professionals looking to leverage AI without compromising on procedure reliability.
Detailed Description: The narrative outlines the author’s transition to using AI in their startup research process, revealing critical insights into how AI is reshaping enterprise workflows. Below are the main points distilled from the text:
– **Integration of AI Tools**: The author migrates their startup research workflow to incorporate various AI tools that enhance productivity without altering the fundamental structure of the workflow.
– **Workflow Classes**:
– **Deterministic Workflows**: These represent traditional processes with exact repetition in execution, serving well for mechanization.
– **AI-Enhanced Deterministic Workflows**: In this setup, standard steps of research remain intact, while AI tools, like ChatGPT and Gemini, perform specific tasks, increasing efficiency while maintaining human oversight.
– **Agentic Workflows**: This type allows AI to make autonomous decisions about the workflow, suitable for scenarios with variable inputs, such as customer support or security incident responses.
– **Benefits Observed**:
– **Simplicity**: The author finds that programming with AI simplifies certain tasks, enhancing categorization accuracy beyond traditional rule-based approaches.
– **Control vs. Autonomy**: The author emphasizes a preference for AI tools to enhance deterministic processes rather than fully entrusting decision-making to AI at this stage. This approach balances consistency with intelligent analysis, which is essential for compliance and operational reliability in enterprise settings.
– **Future Considerations**: While the author contemplates the potential shift toward fully agentic workflows in the future as AI systems improve, they currently favor the hybrid model. This allows them to maintain a structured methodology that benefits from advanced AI capabilities, a key consideration for professionals looking to balance innovation with reliability in their security and compliance frameworks.
The discussion is particularly relevant to professionals in AI and cloud security, as it illustrates practical applications of AI in maintaining security processes and enhancing operational efficiency without compromising control.