A thesis on how agents will transact

What if the best
interface is
no interface at all?

AI agents are starting to act on behalf of people — comparing, choosing, and transacting without visiting a single website. But an agent can only do what it has a skill for. Agentsform is where an agent comes when it hits a task it can’t finish: it describes the skill it needs, we build it, the agent pays for it, and it gets on with the job.

Describe it The agent asks, in plain language
We build it A callable skill, on demand
Agent pays And finishes the task it started

An agent needs a skill
it doesn’t have yet.

A person asks their AI to do something real — order the groceries, book the truck, switch the energy plan. The agent has the intent but no way to act. That’s the moment Agentsform exists for. Five steps, end to end, with no human clicking through a website.

01 · Hits a wall

The agent is mid-task and there’s no skill for what comes next. Today that’s where the agent stops and hands back to a human.

02 · Describes the skill

The agent comes to Agentsform and describes, in natural language, the capability it needs — the inputs it has, the outcome it wants.

03 · We build it

Agentsform turns that description into a real, callable skill: wired to the right service, tested, and exposed over the Model Context Protocol.

04 · Agent pays

The agent pays for the skill it just got — per use, agent-to-agent. No seat licence, no human in the billing loop.

05 · Completes the task

The agent invokes the new skill and finishes what it set out to do — the grocery order placed, the truck booked, the plan switched.

… and keeps it

The skill doesn’t vanish. It’s published to the registry, so the next agent that needs the same capability can just call it.

The primary interface
between businesses and
customers is changing.

We think the next step isn’t a better website or app.
It’s a callable capability, a skill that an AI assistant can discover, evaluate, and execute on behalf of the user.

2010 You need a website
2015 You need an app
2020 You need a platform
2026 You may need a skill

This is a bet, not a certainty. But the trajectory is clear: as AI agents become more capable, businesses that can be executed, not just browsed, will have a meaningful advantage.

  • Static landing pages
  • Manual comparison shopping
  • Multi-step checkout flows
  • Account portals and dashboards
  • Decision fatigue across tabs
  • “Which provider should I use?”
  • Skills built on demand for agents
  • Agent-to-agent negotiation
  • Autonomous purchasing flows
  • Outcome-oriented interaction
  • Zero-interface execution
  • “My AI handles that.”

A customer talks
to their AI.

In Claude, ChatGPT, Gemini, or any assistant. The customer speaks naturally. The agent finds the right skill, or asks Agentsform to build it, executes it, and reports back.

“Order the usual groceries but swap the chicken for lamb this week.”

The agent loads your preferences, adjusts the list, compares prices across stores, builds the cheapest basket, and places the order.

Retail

“Book me a flight to Sydney on Sunday, returning Monday. Window seat if possible.”

The agent queries airline skills, compares prices across carriers, selects the best option, books the ticket, and sends the confirmation.

Airlines

“Get me a moving truck next weekend. I’m moving from Carlton to Footscray.”

The agent checks availability across rental providers, compares rates for the right truck size, books the slot, and confirms pickup details.

Vehicle hire

“My electricity bill seems high. Is there a cheaper plan?”

The agent pulls your current usage, queries energy provider skills, calculates savings, and switches you to a better plan.

Utilities

“I need car insurance for a 2019 Mazda 3. Compare a few options.”

The agent queries insurance provider skills with your vehicle details, returns a comparison table, and can bind the policy on your approval.

Financial services

“Renew my driver’s licence. It expires next month.”

The agent checks eligibility, fills the renewal form, pays the fee, and schedules any required appointment.

Government

We built Gombwe
to test this thesis.

Gombwe is an open-source autonomous agent runtime built on Anthropic’s Claude. It doesn’t just answer questions. It executes real transactions in the real world. It’s how we prove a described skill can become a working one.

See all the skills, native tools, and architecture →

Live in production

Digital family assistant

A single agent that manages the household. Meal planning with automatic ingredient extraction and price comparison across Coles and Woolworths. School schedule management. Grocery ordering with the cheapest basket delivered to your door. Family members, dietary needs, and pantry tracking. All handled.

1 Meal plan set
2 Ingredients extracted
3 Prices compared live
4 Cheapest basket ordered
5 School events tracked
Live in production

Utility plan auto-switching

Continuously monitors energy, internet, and phone plans across providers. When a cheaper option exists, it switches automatically. Not once a year at renewal, but whenever the savings justify it.

1 Plans scraped
2 Savings calculated
3 User notified
4 Switch executed
Architecture

Skills, not screens

Declarative skill definitions. A completion loop with retries and verification. Multi-channel support across Discord, Telegram, and web. Scheduled automation via cron. Two-phase ordering with user confirmation.

gombwe
$ npm install -g claude-gombwe
$ gombwe init
Setting up config at ~/.claude-gombwe/
Skills loaded: grocery-order, morning-briefing, web-monitor
$ gombwe start
Dashboard running at http://localhost:18790
WebSocket ready. Telegram connected. Discord connected.
Scheduler active. 3 jobs loaded.
$

Skills as
open infrastructure.

Every skill we build is published as an MCP server any AI assistant can call. Search products, compare prices, execute transactions — all through the Model Context Protocol standard. Build once, callable by any agent.

More coming

Airlines, vehicle hire, utilities, insurance, government services. Each one a standalone MCP server that any AI assistant can connect to.

Browse the full MCP registry →

Want a skill built? →

The opportunity
beyond convenience.

The same system that compares grocery prices in Melbourne could work with stores like OK or Bon Marché in Harare. Find the cheapest basket, optimise exchange rates, coordinate delivery to family homes.

In markets where infrastructure is leapfrogged routinely, where landlines were skipped for mobile and branches were skipped for M-Pesa, AI-native commerce could follow the same pattern.

600 million people will be online in Africa by 2030. Many may never interact with traditional e-commerce the way the West did. If we’re right about the direction, skill-based commerce could be how they start.

600M+ Projected internet users in Africa by 2030
$300B Projected African e-commerce market by 2030
1.4B People across the continent

When agents come asking,
be reachable.

Every skill an agent buys points at a real service. If your customers are starting to use AI assistants, those assistants will need a way to reach you. We build that integration so an agent can transact with you directly.

Airlines

Flights as bookable skills. A customer says “fly me to Sydney on Sunday” and the agent handles search, seat selection, and payment.

Vehicle hire

Cars, trucks, vans. “Get me a moving truck next weekend.” The agent checks availability, compares rates, and books it.

Retail

Your catalogue as a skill. AI agents browse, compare, and purchase on behalf of customers without a storefront.

Financial services

Insurance quotes, loan applications, plan comparisons. Structured for execution by a customer’s AI assistant.

Utilities

Expose plans as queryable skills. Compete on value delivered, not on landing page conversion rates.

Government

Permit applications, benefit eligibility, registrations. Accessible without portals, queues, or forms.

Try Gombwe yourself.

One command. Installs everything you need.
Works on macOS and Linux. Requires an Anthropic API key.

1
curl -fsSL https://gombwe.com/install.sh | bash
2
gombwe init
3
gombwe start

Open localhost:18790 and your agent is ready. Connect Discord, Telegram, or use the web dashboard. Define skills. Schedule jobs. See what’s possible.

We could be wrong
about the timing.

But the direction seems clear. AI agents are getting more capable, and the interface layer between businesses and customers is going to shift. We’d rather build for that future early than react to it late.

If you’re thinking about this too, whether you’re at Anthropic, Google, Econet, or anywhere else, we’d welcome the conversation.

Tendai Mudavanhu

Melbourne, Australia

Originally from Harare, Zimbabwe