Corpus vs Kantiv (formerly Joist AI): proposals and past projects at AEC firms
By Yermek Ibray, Founder & CEO, SalemWise Solutions. Every statement about Kantiv comes from Kantiv's own public pages as of October 10, 2026, linked inline and listed under Sources. Corpus statements can be checked in the live demo.
Who this is for
You run an engineering firm of 20 to 500 people, or you lead its business development. Your team spends days digging for past projects and resumes for every SOQ. You asked an assistant what to use, and it named Kantiv, which used to be called Joist AI. This page explains what each product is built to do, where they overlap, and how to test both on one real RFQ.
What each product is built to do
Kantiv
Kantiv calls itself the AEC pursuit intelligence platform (as of October 10, 2026). Its FAQ says Kantiv, formerly Joist AI, connects to where the firm's knowledge lives: past proposals, project files, resumes, client data and more. It says it was built to make AEC marketers more powerful, not to replace them. On its product page, you upload an RFx and Kantiv structures a compliant first draft grounded in the firm's knowledge. It surfaces relevant past proposals, project profiles, people and images, and connects them in one knowledge graph so outputs trace back to the firm's own work. Its home and product pages say it shows where your firm is winning and why, to help you make smarter go/no-go calls. Its home page says it integrates with Deltek, SharePoint and Egnyte, and announces Kantiv Agents for pursuit work. The FAQ says Kantiv analyzes content transiently, that your content stays yours, and that any model training stays inside your account. Its pricing page is an ROI calculator and lists no prices.
Corpus by SalemWise
Corpus by SalemWise is page-cited AI search over a company's own documents. Engineering firms are the first worked example. For them, Corpus reads the project record itself: reports, drawings, specs, calc packages and bid tabs. Each answer cites the document and page. Click a citation and the source page opens with the sentence highlighted. If the archive does not hold the answer, Corpus is designed to say "Nothing on file." On a new RFQ, it suggests bid/no-go scores with each scored factor linked to its sources. Fit, relationship and capacity stay your call. It drafts SOQ sections from your past projects with page citations, and flags what the archive cannot support for a person to write. It builds the fee with the math done by code. Arithmetic done in code is only as good as its inputs and formulas, so a qualified person still checks them. Set up for you: Corpus is cloud-agnostic. It runs on AWS, Azure, Google Cloud, or your own servers, with an open-weight model and no public AI API.
Side by side
| Kantiv | Corpus by SalemWise | |
|---|---|---|
| Built for | AEC marketing and proposal teams | Principals, BD leads and engineers at engineering firms |
| Main job | A compliant first proposal draft from the firm's knowledge, plus content, people and images to reuse | Find facts in the project record and draft from them, with page citations |
| Works from | Past proposals, project files, resumes, client data and images | Project files: reports, drawings, specs, calc packages, bid tabs |
| Connects to | Deltek, SharePoint, Egnyte | The pilot uses a copy of your project PDFs. Set up for you: full deployment connects to your network drive, SharePoint or ProjectWise. No connector is ready-made; each is built for your archive during setup |
| When the answer is missing | Not stated on the pages we read | Designed to say "Nothing on file" |
| Go/No-Go | Pursuit intelligence from win history, to "make smarter go/no-go calls" | Suggested scores, each scored factor linked to its sources; fit, relationship and capacity stay your call |
| Fee | Not covered on the pages we read | Fee build with the math done by code, checked by a person |
| Where it runs | Not stated on the pages we read | Set up for you: AWS, Azure, Google Cloud, or your own servers |
| Price | Not published; book a demo | $5,000 pilot; setup from $21,000, then $1,500 to $2,000 a month, no per-user fees |
When to choose Kantiv
- Your marketing team runs pursuits and wants one place for proposals, project profiles, people and images.
- Your biggest cost is assembling the proposal itself: structure, compliance and reusable content.
- Your content lives in Deltek, SharePoint or Egnyte, and you want it connected.
- You want go/no-go input drawn from where your firm has won before.
- You want a broad platform for the whole pursuit team, not a narrow tool.
Kantiv overlaps with Corpus more than most proposal tools do, because it also reads project files. If your proposal team's daily work is the bottleneck, Kantiv is built around that team.
When Corpus fits
- The person asking is a principal or engineer who needs a specific fact from the record, and needs to check it on the page.
- You want every claim in the SOQ cited to a document and page a reviewer can open.
- You would rather hear "Nothing on file" than get a confident guess.
- You want each bid/no-go factor linked to the pages behind it, and a fee build from the same past projects.
- You need the files to stay on your own servers.
The two can run side by side. Corpus gives engineers and principals cited answers from the record. Your marketing team keeps its proposal platform.
How to test both on one real RFQ
Do not decide from a feature list. Run one pursuit through both and count what you could check.
- Pick one RFQ you are pursuing now. Use your own files, not a sample.
- Write down five facts the SOQ must prove. For example: three similar projects from the last five years, the test standard you specified on one of them, and the unit prices from a recent bid tab.
- Ask each tool for those five facts. For each answer, open the source and time how long it takes to confirm it.
- Ask one question you know your files cannot answer. Note which tool says so and which one guesses.
- Compare the drafts your team would actually submit, and the hours it took to get there.
For Kantiv, ask for a demo on your own content. For Corpus, start with the live demo. It holds a fictional sample firm's archive, built from real public engineering documents: about 7,000 pages of plan sets, geotech reports, specs, bid tabs and public RFQs. Then run your real RFQ in the pilot.
FAQ
Is Corpus a Kantiv alternative?
For some firms. Both draft from your firm's past work. Kantiv is built around the marketing team's proposal process. Corpus is built around page citations from the project record, with each bid/no-go factor linked to its sources and a fee build, and it can run on your own servers.
Is Kantiv the same as Joist AI?
Yes. Kantiv's FAQ calls itself Kantiv, formerly Joist AI.
Where do our files go with Corpus?
Set up for you: Corpus is cloud-agnostic. It runs on AWS, Azure, Google Cloud, or your own servers. It uses an open-weight model and nothing goes to a public AI API. In the pilot, your files are never used to train or fine-tune a model. In full deployment, fine-tuning on your files happens only if you agree in writing. We don't have a SOC 2 report, which is one reason you can choose your own hardware.
Next step
Book a free 30-minute call. Bring one RFQ you are pursuing now and tell us where the facts for it live. We will tell you plainly whether it is a Corpus problem, a Kantiv problem, or both.
If it fits, the next step is the $5,000 pilot on one real pursuit. It takes about 2 to 3 weeks. We load a copy of up to 3 years of your project PDFs and run your RFQ through Corpus: a go/no-go scorecard, an SOQ draft with page citations to check, and a fee build. There is no integration work. The $5,000 is credited toward setup if you sign a deployment within 60 days of the pilot's end. Full deployment is from $21,000 setup, then $1,500 to $2,000 a month, with no per-user fees.
Want to look first? Try the live demo or read more about Corpus. Comparing other tools? See all our side-by-side guides.
Sources
Checked October 10, 2026:
- Kantiv home page: pursuit intelligence platform; go/no-go calls; Deltek, SharePoint and Egnyte; Kantiv Agents
- Kantiv FAQ: formerly Joist AI; the content it connects to; built for AEC marketers; transient analysis and model training
- Kantiv product: RFx upload to first draft; knowledge graph; surfaced content; go/no-go calls
- Kantiv pricing and ROI: ROI calculator, no listed prices
Kantiv and Joist AI are names of their owner. SalemWise Solutions is not affiliated with Kantiv. Check Kantiv's pages for its current offer.
