Joppa Technologies — Applied AI studio

AI that acts,
not just answers.

We engineer the harness and memory layer around frontier models — turning raw intelligence into agents you can depend on. Software that doesn’t just answer; it acts, with a human on the decisions that count.

Built on a modern AI stack
ClaudeGoogle WorkspaceStripeSupabaseRender
Our mission

We believe technology should give people back their most finite resource — their attention.

Not by replacing the work that matters, but by carrying everything around it — so a person who runs a business one relationship at a time is free to do the part only they can do.

Our first product, Zora, does this for event professionals: it reads the inbox, drafts replies, holds the calendar, and sends invoices on its own — with a human on every decision that counts. Beneath it: a dependable harness and a memory that compounds.

What we build

Agent equals model plus harness.

A frontier model is the smallest part of a working agent. The reliability lives in the harness around it, the memory beneath it, and the evals that prove it. That's what we engineer.

01

Agent harnesses

The runtime around the model — orchestration, control loops, tool use, with a guardrail on every step. What turns a clever demo into an agent that holds up in production.

02

Memory & retrieval

A memory layer with retrieval (RAG) so the agent remembers across sessions and grounds every answer in your real data — not the model’s guesses.

03

Evals & fine-tuning

We measure reliability with evals, then sharpen behavior with fine-tuning. What gets measured is what you can trust.

04

Systems of action

The whole workflow, inbox to invoice — shipped as a production app that plans, acts, and verifies, with a human in control.

Inside the harness

What we engineer around the model.

"Harness" isn't a metaphor — it's a concrete stack of runtime components. Hover the diagram below to see how they work together.

01

Instructions

The agent’s job, rules, and tone.

02

Tools & MCP

Permissioned actions over the Model Context Protocol.

03

Orchestration

Plan, act, reflect — across sub-agents.

04

Verification

Every output checked against the truth.

05

Guardrails

Hard limits; prompt-injection defense.

06

Observability

Full tracing of every step.

07

Sandboxing

Isolated, contained execution.

08

Cost control

Token budgets and prompt caching.

Context
Request
Instructions
Memory & retrieval
Orchestration
Planner agent
Agents
Drafting agent
Scheduling agent
Billing agent
Reasoning
LLMthe model
Tools & MCP
Sandbox
Safety
Verification
Guardrails
Output
Action ✓
Cross-cutting
Observability
Cost control
The harness, layer by layer
Hover any block to see what it does. A request flows left to right — grounded in memory, planned by the orchestrator, carried out by specialist agents over the model and tools, checked by verification and guardrails, and out as an action you approve.
hover any component · observability & cost control watch every layer
Our thesis

Any model can ace a demo. Only a harness survives production — so that's the part we build.

Proof of work

Zora — built, shipped, running.

Zora is a production system of action for event professionals — one tool replacing five, running the client workflow end to end.

Product — live in production

The AI back-office for event pros.

An agent harness over a memory layer: it reads the inbox, drafts quoted replies in the planner's voice — checked against their real pricing — manages the calendar, sends invoices, and gives each client a branded portal. One system where there used to be five.

5 → 1
Tools replaced
Memory layer
Per-business context
Verified
Every draft fact-checked
Human-in-loop
You approve every send
Let's build

Have a workflow worth automating?