Skip to content
AI NEWS#agents#llms Oct 22, 2026 · 6 min read

AI agents are leaving the demo stage. Here’s what to build now.

Agentic tools were the headline of almost every AI launch this month. The demos are impressive — but the teams getting real value share four boring, reliable patterns.

YNDeepak KumarAI/ML Engineer

What changed this month

If you followed tech news in October, you saw the word “agent” everywhere — in model launches, developer tools and enterprise announcements. The pitch is the same each time: give a model tools, a goal and some autonomy, and let it finish the job.

The gap between that pitch and production is still wide. Agents that look magical in a two-minute demo loop forever, call the wrong tool, or confidently do the wrong thing when real users show up. The teams shipping agents successfully aren’t using a secret model. They’re using four unglamorous patterns.

1. Constrain the tools

An agent is only as safe as the tools it can reach. Start with a short allowlist of narrow, well-described tools — “search the help center”, not “run any SQL”. Read-only tools first; anything that writes, sends or spends money gets its own review step.

agent.py · python
ALLOWLIST = {"search_docs", "read_ticket", "draft_reply"}

def run_agent(task, llm, tools, max_steps=8, budget_usd=0.50):
    spent, history = 0.0, []
    for step in range(max_steps):
        action = llm.decide(task, history, tools=ALLOWLIST)

        if action.name not in ALLOWLIST:
            return handoff(task, reason="tool not allowed")
        if action.confidence < 0.6:
            return handoff(task, reason="low confidence")

        result = tools[action.name](**action.args)
        spent += action.cost
        history.append((action, result))
        log_step(task.id, step, action, result, spent)

        if action.is_final or spent > budget_usd:
            break

    # never fail silently: no result means a human takes over
    return history[-1][1] if history else handoff(task, reason="no progress")

2. Budget every run

Agents fail in loops. Put hard limits on steps, wall-clock time and cost for every single run, and treat hitting a limit as a normal outcome, not an exception. A run that stops at step eight with a clear “I couldn’t finish” is far better than one that burns through your API budget overnight.

3. Hand off when unsure

The most valuable feature of a production agent is knowing when to stop. Design the handoff first: what the human sees, what context is attached, and how their decision flows back. Users forgive “I’ve passed this to a teammate” far more easily than a confident mistake.

KEY TAKEAWAY

Autonomy is a dial, not a switch. Start an agent at “suggest”, earn “act with approval”, and only then “act alone” — task by task.

4. Log every step

You can’t improve what you can’t replay. Trace every run end to end — it’s also how you build the evaluation set that makes the next version better.

LOG THISSO YOU CAN
Prompt, model and versionReproduce any run exactly
Each tool call and its argumentsAudit what the agent actually did
Tokens, latency and cost per stepCatch runaway loops early
Outcome and human feedbackTurn real runs into test cases

Where agents still fall over

  • Long, open-ended tasks. Errors compound with every step; ten mostly-right steps can still add up to a wrong result.
  • Ambiguous goals. “Clean up the CRM” means something different to every person who says it.
  • Untrusted inputs. Web pages, emails and documents can carry instructions the agent shouldn’t follow — treat them as data, never as commands.
  • Irreversible actions. Payments, deletions and outbound messages still need a human in the loop.

What I’d build this quarter

Pick one narrow, repetitive workflow your team already does by hand — triaging support tickets, drafting first replies, summarising pull requests. Give the agent three read-only tools, a step budget and a clear handoff. Measure it against the manual process for two weeks. If it wins, widen the scope one tool at a time.

That’s less exciting than a fully autonomous assistant. It’s also the version that will still be running next year.

YN
WRITTEN BY Deepak Kumar AI/ML engineer building LLM applications and the infrastructure behind them. Open to new roles and collaborations.
$ ls ~/blog --related
All posts