Skip to content
Art2link ESB HomeDocumentationBlogContact
Updated July 21, 2026
AI features/AI Accelerator

AI Accelerator

Four ways to put the Accelerator to work, three guided modes, one per artifact, and one free-form mode for everything else.

Each guided mode is a structured prompt that produces one specific kind of output; the reasoning behind them is covered below. The free-form mode is the catch-all: a single open prompt that can do anything the guided modes do.

More guided modes will be added over time as new artifact-specific workflows are validated.

The name is deliberate. The AI Accelerator is where domain knowledge lives, and that knowledge covers the message standards integration work actually runs on. It already understands the major EDI, healthcare, financial, supply-chain, and general-purpose formats, so you do not have to teach it a specification before you can put it to work. Ask it to disassemble an EDI 810, validate an EDIFACT ORDERS, parse an HL7 ADT feed, read a HIPAA 837 claim, or handle a SWIFT MT103, and it gets to work: no add-on, no package to license, no separate install.

Everything BizTalk shipped an accelerator for, and a great deal more, is already in the knowledge base:

StandardRepresentative transaction types
EDI (X12)850 purchase order, 855 PO acknowledgement, 860 PO change, 810 invoice, 856 advance ship notice, 846 inventory advice, 820 payment/remittance, 830 planning schedule, 940/945 warehouse shipping, 204/210/214 transportation, 997/999 acknowledgements, and the rest of the set.
EDIFACTORDERS, ORDRSP, DESADV, INVOIC, DELFOR, RECADV, IFTMIN, PRICAT, CONTRL, APERAK, and the wider UN/EDIFACT directory.
HL7Clinical and administrative messages such as ADT, ORM, ORU, SIU, MDM, DFT, and MFN, down to the segment and field level.
HIPAA (healthcare X12)837 claims, 835 remittance advice, 270/271 eligibility, 276/277 claim status, 278 authorization, 834 enrollment, 820 premium payment.
FHIRResources and bundles (Patient, Observation, Encounter, and the rest) for modern healthcare interoperability.
SWIFTMT messages such as MT103, MT202, MT940, and MT950, plus the ISO 20022 MX equivalents.
RosettaNetPIPs such as 3A4 purchase order, 3B2 advance shipment notice, and 4B2 shipment receipt.
ISO 20022Payment and cash-management messages, the pain, pacs, and camt families.
SAP IDocCommon IDoc types including ORDERS, INVOIC, DESADV, and DELVRY.
Flat files, CSV, JSON, XMLThe everyday formats too, fixed-width and delimited files, JSON, and XML.
The table is a starting point, not the boundary. The AI Accelerator’s model is aware of essentially every message standard in common use, well beyond the list above. If you work with something that is not shown here, do not assume it is unsupported, just ask. Prompt it directly, for example “What message standards and formats can you work with?” or “Can you disassemble an EDIFACT DESADV?”, and it will tell you what it can handle before you commit to a build.

If you are coming from BizTalk, this is where the accelerators went. On BizTalk you installed a separate accelerator for each domain, EDI, HL7, SWIFT, RosettaNet, and so on, before the engine knew how to handle those formats. In Art2link ESB that knowledge is embedded in the AI Accelerator’s knowledge base. The same request that used to require the right accelerator on the box is now just a prompt.

ModeWhat it buildsStyle
Pipeline componentA custom pipeline component, today the disassembler workflow is supported; more component types will follow.Guided
Custom functionA custom function, the C# method, the [CustomFunction] attribute, and the call-site usage.Guided
MapAn Art2link map, the XSLT, the source/destination shape alignment, and any helper-function calls.Guided
Free-formAnything, you describe the goal and provide the context; the Accelerator produces whatever the prompt asked for.Open prompt
What do youneed built?Pipeline componentCustom functionMapAnything else, or severalartifacts in one requestGuided modethe form asks for exactly theinputs that artifact needsFree-form modeone open prompt, you supply the context
When the Accelerator knows in advance what kind of artifact it’s building, it can ask for exactly the information that artifact needs, instead of leaving you to guess what to share. A free-form prompt only works as well as what you give it.

Free-form is a single open prompt with no shape imposed on it. It can produce any of the artifacts the guided modes produce, and anything else the Accelerator is capable of.

Use free-form when:

  • The task doesn’t match any guided mode (questions about your environment, exploratory analysis, ad-hoc generation).
  • You already know exactly what context the Accelerator needs and prefer to type it once rather than fill a form.
  • You want to combine several artifacts in one request (e.g., a custom function and the map that calls it).
⚠️
The Accelerator cannot build an integration end-to-end. It can generate the individual artifacts described above, pipeline components, custom functions, maps, but it cannot today wire up a receive port, a routing rule, a map, and a send port into a working flow on your behalf. Whole-integration generation is in active development, targeted for August 2026, but the date is not yet committed.
Included in all editions.