Notes on getting work done by agents
Comparisons, prices as of this month, and what actually works when you hand a task to an AI agent. Written by the people who build and test them.
AI Agent Prompt Engineering: 5 Parts of a Production Prompt
Prompt engineering for AI agents is not the same craft as prompt engineering for chatbots. A chatbot prompt shapes one response. An agent prompt shapes a loop: the model picks a tool, reads the result, decides…
Multi-Agent Coordination Patterns: Supervisor, Peer, Market, Shared-State
The intuition that "more agents will do better than one agent" is wrong more often than it is right. Most production multi-agent systems exist because the work has genuine boundaries (different access controls,…
AI Agent Integration Patterns: Webhook, OAuth, MCP, Polling, Queue
Most AI agent failures in production are not model failures. They are integration failures. A webhook arrives twice and the agent acts twice. An OAuth refresh fails silently and the agent runs unauthenticated. A…
AI Agent Data Residency: EU, India, US Architecture Patterns
Data residency is one of the silent gating items for enterprise sales of AI agents. The product can be perfect, but if the prompts leave the EU, the deal dies. This guide is the architecture playbook for…
AI Agent Audit Trails: What to Log, Keep and Protect in 2026
An AI agent audit trail is a time-ordered, tamper-evident record of what an agent did on each run: what happened, when and where, from what source, with what outcome and under whose identity, plus each tool call and…
AI Agents for SaaS Founders: Where They Actually Earn Their Keep
The honest pitch for AI agents to a SaaS founder is not "scale your team." It is "stop dropping the recurring five-to-fifteen-minute tasks that compound into churn." Most SaaS founders I talk to do not have a…
AI Recruiters in 2026: What They Screen and What They Miss
An AI recruiter is good at the half of recruiting nobody wants to do. It is dangerous at the half that decides someone's job.
AI Agents for Real Estate Agents: The Compliant Lead-and-Listing Stack
Real estate is one of the few industries where a single AI agent can be the difference between converting a lead and losing it to a faster competitor. Inbound buyer leads are perishable in a way that almost no other…
AI Agents for Marketing Agencies: The Real ROI Map
For most small-to-mid marketing agencies, AI agents are the difference between a 12% net margin and a 28% net margin on the same retainer book. Not because the agency hires fewer people, but because the agents soak…
AI Agents for Freelance Designers: Run the Studio, Not the Drudgery
The honest job description for a freelance designer is "two roles in one person." Half the week is design work; half the week is studio operations. Intake calls. Scope clarification. Proposal drafts. Asset packaging.…
AI Agents for Content Creators: Run the Distribution, Keep the Taste
Content creators in 2026 face a paradox. The tools to make and distribute content have never been more powerful, and the audience tolerance for AI-generated work passing as human has never been lower. The creators…
AI Agents for Consultants: The Proposal-to-Deliverable Stack
Consulting is a profession built on judgment, but a typical engagement is filled with the supporting work that produces the conditions for judgment: research, synthesis, slide drafting, meeting prep, status…
AI Agents for Accountants: The Reconciliation, Categorisation, and Client-Chase Stack
Accountants and bookkeepers face two pressures pointing in the same direction. Clients increasingly expect monthly close in five business days instead of fifteen. Margins on transactional bookkeeping are compressing…
AI Agent Security Best Practices: A 2026 Production Playbook
Most security guides written for large language models stop at the prompt boundary. They assume a single completion, no tools, no state, no autonomy. That model has not described production deployments for at least…
AI Agent Monitoring and Observability: A 2026 Production Playbook
The first time I shipped an agent without proper observability I did not notice quality degradation for nine days. Token costs were stable, latency was fine, error rates were nominal. The agent was answering…
AI Agent Governance and Compliance: A 2026 Operating Guide
For most of 2024 and the first half of 2025, AI governance for agents was a tomorrow problem. By mid-2025 it had become a this-quarter problem. The EU AI Act began entering force in stages, the NIST Generative AI…
AI Agent Cost Optimization: A 2026 Tactical Playbook
This is not a primer on AI agent pricing models. The taxonomy of per-token, per-task, per-agent, and capability-based pricing already lives at AI agent cost models explained. This piece is the operational sibling.…
Gravity vs Workato: Enterprise iPaaS vs Self-Serve Runtime (2026)
Workato and Gravity get put on the same shortlist when a buyer types "AI workflow automation" into Google and the search engine hands back both. The shortlist is misleading. Workato is an enterprise iPaaS. Gravity is…
Gravity vs Tray.ai: Low-Code Platform vs Sentence Runtime (2026)
Tray.ai and Gravity both ride the AI automation wave, but the buyer and the building experience are different. This comparison helps decide which category fits the work you have.
Gravity vs Relay: Human-in-the-Loop vs Outcome Runtime (2026)
Relay and Gravity both target the "AI drafts, human approves" pattern. The category framing is different. Relay puts the workflow first and the AI inside a step. Gravity puts the outcome first and approval inside the…
Gravity vs Pipedream: Code Steps vs Sentence Runtime (2026)
Pipedream and Gravity get lined up a lot because both can "take a Slack message and do something useful with it." The interface is different, the buyer is different, and the unit of work is different. This is a…
Gravity vs IFTTT: Consumer Triggers vs Autonomous Agents (2026)
IFTTT and Gravity get compared mostly because IFTTT was, for a generation of automators, the entry-level idea of "let one app talk to another." If the same buyer evaluates Gravity today, the question is whether AI…
Best Zapier Alternatives Using AI in 2026: Real Agents, Not Steps
Update, 10 October 2026: on 6 October Zapier announced that Zapier Agents is now AI by Zapier. An agent's instructions, tools and trigger now live in one AI step inside a Zap. Approvals can be set per tool, and the…
Best Manus Alternatives in 2026: Recurring Agents, Not One-Off Tasks
Manus took off because it could pick up a vague task description and run a multi-hour autonomous session. That demo is impressive. The follow-up question buyers ask is "does it run every Monday at 9am for me,…
Best Lindy Alternatives in 2026: A Founder's Shortlist
Lindy markets itself as "AI employees" and ships a clean visual flow builder with strong defaults. Most "Lindy alternative" searches start because a buyer hit one of three things: pricing, the canvas being too much…
Best LangChain Alternatives for Non-Developers in 2026
If you have ever read the LangChain docs and thought "I just want the thing to work, not learn another framework," this list is for you. LangChain is a powerful Python library. It is for engineers. Non-developers who…
Best ChatGPT Workspace Agents Alternatives in 2026
ChatGPT Workspace Agents shipped in April 2026 and immediately changed the shortlist for any buyer evaluating "AI agents for my team." If your company is already on ChatGPT Business or Enterprise, agents are bundled…
Gravity vs TinyFish: Enterprise Web Agent vs Runtime (2026)
This comparison covers two products that buyers often line up against each other when they shouldn't. TinyFish is an enterprise web agent platform. Gravity is an outcome runtime. The labels look similar at a glance,…
Gravity vs OpenClaw: Browser Agent vs Outcome Runtime (2026)
This comparison covers two products that buyers often line up against each other when they shouldn't. OpenClaw is a browser-driven autonomous agent. Gravity is an outcome runtime. The labels look similar at a glance,…
Gravity vs MindStudio: AI App Builder vs Runtime (2026)
This comparison covers two products that buyers often line up against each other when they shouldn't. MindStudio is a no-code AI app builder. Gravity is an outcome runtime. The labels look similar at a glance, the…