category
At 2 a.m., a bank's nightly batch is still running: job scheduling, reconciliation, the general ledger, and reports.
This is not a toy workload. It sits in banking, insurance, government, and airlines, where the system is old enough to have change control and important enough that nobody wants to rediscover its edge cases. A load-bearing batch program is not just code. It holds transactions, reconciliation, audit trails, and change-control knowledge that have survived for decades because they work.
Default answer one: migrate
The first default answer is to migrate the COBOL to Java or C#, or put the agent in a Python or Java sidecar.
Migration can be correct. But for a system that already owns transactions, operational knowledge, and audit history, migration is a revalidation program, not a syntax cleanup.
Default answer two: bridge
The second default answer is a sidecar. The GnuCOBOL 2.0+ program exposes a tool or API, and a new service owns the agent loop.
This is often the right engineering choice. It isolates the new runtime and avoids touching fragile code. But the governance boundary moves with the agent. Policy, approvals, credentials, checkpoints, and audit events now cross a process or network boundary.
The third path: keep the runtime
PRAXO-CORE puts the loop where the work already lives.
The application calls praxo-run with options, a session, and a prompt. Model callbacks, tools, policy, and events remain in the same process or runtime. The loop is a library; the application still owns the provider, tools, policy content, and deployment.
What native COBOL means
The implementation is GnuCOBOL 2.0+. Distribution: source tag cobol/v0.8.0; no package-registry release.
The Core is not a hosted service. It does not own credentials or tenant data. It provides a governed execution boundary, and the application provides the business controls around it.
Architecture highlights
- Native GnuCOBOL, not a bridge.
- 63 normative vectors across 11 groups.
- OpenAI-compatible, Anthropic, Gemini, MCP, OTel, retriever, delegation.
The important design choice is not the number of modules. It is that the final tool arguments are reauthorized after edits, denials leave zero effects, and events can be audited.
The limits are the design
- JSON input: 32,768 bytes, 512 nodes, 64 nesting levels; generated JSON: 16,384 bytes.
- Bounded ASCII schema patterns; unsupported patterns fail explicitly.
- Path policy is lexical, not OS confinement.
- Email redaction only; not general PII.
- Synchronous events and streams; not an async runtime.
These limits make failure modes reviewable. A bridge or sidecar may still be better when isolation, deployment ownership, or team boundaries matter more than an in-process loop.
Governance
For banking, insurance, government, and airlines, the question is not “Can COBOL call a model?” It is whether an agent can participate in a regulated or operational process without bypassing the controls around it.
The Core handles execution. The application still owns identity, policy decisions, approvals, effect records, isolation, shutdown, and the meaning of the tool call.
What we did not do
- We did not claim full Go parity.
- We did not claim a hosted agent platform.
- We did not claim production readiness or a security certification.
- We did not claim that migration or a bridge is obsolete.
Invitation
If you run banking, insurance, government, and airlines, I would value the hard questions. What would you test first? Which boundary should stay native, and which should remain behind a bridge or sidecar? What evidence would you need before letting an agent touch a production tool?
A useful answer can be “a sidecar is the right fit.” The goal is an honest integration boundary, not one architecture for every system.
Repo: https://github.com/axisvela/praxo-core
Language docs: https://axisvela.github.io/praxo-core/languages/cobol/
Canonical: https://architect.pub/cobol-batch-agent-deep-dive
- 登录 发表评论