we build

Infrastructure for agentic decision-making

Decisions are moving from people to agents. Enterprise decision-making is increasingly driven by agents planning and acting autonomously across numerous tools. This shift promises significant gains in speed and scale but leaves an enterprise with a fragmented record of how its own decisions are made.

The infrastructure we build returns control of the decision-making record to enterprises. DSI helps them improve their decision-making and unlock the full value from their investments in AI by giving them the ability to govern and learn from their agentic decision ledger.

Pathiqa controls the relationship between agents and enterprise information. Exostrate controls the runtime in which agents execute. Decision Superintelligence Labs conducts research into the formal foundations for safely delegating work to autonomous agents.

Pathiqa · ProductExplore Pathiqa →

Governed infrastructure for integrating enterprise AI

Pathiqa is the infrastructure between an enterprise’s systems of record and its systems of action. It securely connects any AI tool to an organisation’s data, wherever it lives, with every action written into an immutable ledger.

// The ontology

Resolves enterprise data by meaning, creating a consistent understanding across systems that persists independently of where the data is stored.

// The ledger

Records every declared intent, access, action, and outcome as a signed, immutable entry.

// The key

The unit to which scope, access rights and reputation apply, both within the enterprise and across boundaries.

Views · PathiqaSee Views →

A live window into your enterprise

A View is a shareable, continuously updated window into your enterprise. It brings together the numbers and an agent’s interpretation of them, highlights questions you may not have thought to ask about, and lets you explore follow-up questions in the same place. The first View is the Agent Stand-Up: a daily brief showing what your agents did, where they are uncertain, and what needs human attention.

Agent Stand-Up

Treasury Ops

Live · updated 2 min ago
142Invoices resolved
3Exceptions
68%Spend vs budget
// agent · operational assessment

Cash position is healthy. Two counterparties, ACME and Northwind, are slow to confirm, so I’ve queued ACME for manual review. One refund exceeds my policy limit and needs a human decision.

confidence: medium
⚑ 1 refund over policy limit, awaiting your decision
Exostrate · ProductExplore Exostrate →

The agent hypervisor

Ship autonomous AI like you ship containers: governed, isolated, lease-bound, and cryptographically auditable. Package an agent, push it to a Git-coupled registry, lease it into an isolated runtime under a hard budget, and prove every action it takes.

// 01 · Package

Bundle an agent, its dependencies, and its policy into a versioned ExoChart.

// 02 · Push

An immutable content digest and Git provenance, traceable to the exact commit.

// 03 · Lease

An isolated runtime: partitioned compute, encrypted storage, a hard token budget.

// 04 · Govern

Watch it execute, authorize every action, and prove it all against a tamper-evident ledger.

ResearchRead the research →

Building the foundations for trusted AI agency

The technical and organisational foundations needed to delegate important work to AI while maintaining authority, accountability and control, across four programme areas.

// 01

Agent governance and control

Permitting only the actions that keep an acceptable outcome achievable, based on available information and the agent’s authority at its current runtime state.

// 02

Proof-carrying authority

Certificates that prove a governing decision was authorised and carried out exactly as intended, with a governance memory that preserves that certified decision over time.

// 03

Design and reliability

Separating what an agentic system may do from what it actually does, distinguishing potential from realisation and applying minimum necessary permissions based on cost, latency, exposure and risk.

// 04

Organisational adoption

Adoption as a state rather than a score: sustained delegation of consequential work, the evidence loop that holds it in place, and the thresholds that govern entry and exit.

Ready to useExplore Pathiqa →

Ask an agent in a few lines.

Pathiqa works across your existing technology stack. Ask an agent a question and get an answer grounded in governed enterprise data, with every access recorded in the immutable ledger. The same call, in your language.

from pathiqa import Pathiqa

client = Pathiqa()

response = client.ask(
    agent="ag_1e6477e5812e424ef9d087effa4670ec",
    question="How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?",
)

print(response.output_text)
import { Pathiqa } from "pathiqa";

const client = new Pathiqa();

const response = await client.ask({
  agent: "ag_1e6477e5812e424ef9d087effa4670ec",
  question: "How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?",
});

console.log(response.outputText);
import ai.pathiqa.Pathiqa;
import ai.pathiqa.models.AskParams;
import ai.pathiqa.models.AskResponse;

Pathiqa client = new Pathiqa();

AskResponse response = client.ask(AskParams.builder()
    .agent("ag_1e6477e5812e424ef9d087effa4670ec")
    .question("How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?")
    .build());

System.out.println(response.outputText());
package main

import (
    "context"
    "fmt"

    "github.com/pathiqa/pathiqa-go"
)

func main() {
    client := pathiqa.NewClient()

    response, err := client.Ask(context.Background(), pathiqa.AskParams{
        Agent:    "ag_1e6477e5812e424ef9d087effa4670ec",
        Question: "How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?",
    })
    if err != nil {
        panic(err)
    }

    fmt.Println(response.OutputText)
}
use pathiqa::Pathiqa;

let client = Pathiqa::new();

let response = client
    .ask()
    .agent("ag_1e6477e5812e424ef9d087effa4670ec")
    .question("How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?")
    .send()
    .await?;

println!("{}", response.output_text);
require "pathiqa"

client = Pathiqa::Client.new

response = client.ask(
  agent: "ag_1e6477e5812e424ef9d087effa4670ec",
  question: "How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?"
)

puts response.output_text
use Pathiqa\Client;

$client = new Client();

$response = $client->ask(
    agent: 'ag_1e6477e5812e424ef9d087effa4670ec',
    question: 'How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?',
);

echo $response->outputText;
using Pathiqa;

var client = new PathiqaClient();

var response = await client.AskAsync(
    agent: "ag_1e6477e5812e424ef9d087effa4670ec",
    question: "How have time-of-day and day-of-week purchasing patterns changed since the launch of our new ad campaign in Tokyo over the last 3 weeks?"
);

Console.WriteLine(response.OutputText);
News

Catch up on the latest announcements, press releases, and publications from DSI.

Read the latest →
Company

Decision Superintelligence is the company. Pathiqa and Exostrate are its products. Decision Superintelligence Labs is its research programme, and DSI Solutions its advisory and implementation practice.

DSI is hiring. Enquiries regarding the work, the research programme, or collaboration are welcome.